alt.bib

@inproceedings{bayan2026can,
  title = {Can Thinking Models Think to Detect Hateful Memes?},
  author = {Bayan Kmainasi, Mohamed and Kutlu, Mucahid and Ezzat Shahroor, Ali and Hasnat, Abul and Alam, Firoj},
  booktitle = {Proceedings of the Fourth International Workshop on Multimodal Content Analysis for Social Good},
  address = {Dubai, United Arab Emirates},
  publisher = {Association for Computing Machinery},
  year = {2026},
  note = {Co-located with The Web Conference 2026},
  url={https://arxiv.org/pdf/2603.01225},
}

@article{alam2026critisense,
  title   = {{CritiSense}: Critical Digital Literacy and Resilience Against Misinformation},
  author  = {Firoj Alam and Fatema Ahmad and Ali Ezzat Shahroor and Mohamed Bayan Kmainasi and Elisa Sartori and Giovanni Da San Martino and Abul Hasnat and Raian Ali},
  journal = {arXiv preprint arXiv:2603.16672},
  year    = {2026},
  url     = {https://arxiv.org/abs/2603.16672},
}

@inproceedings{abbas2026fanarsadiq,
  title = {{Fanar-Sadiq}: A Multi-Agent Architecture for Grounded Islamic QA},
  author = {Abbas, Ummar and Ouzzani, Mourad and Eltabakh, Mohamed Y. and Sinan, Omar and Bhatia, Gagan and Mubarak, Hamdy and Hawasly, Majd and Hashim, Mohammed Qusay and Darwish, Kareem and Alam, Firoj},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics},
  address = {San Diego, California, United States},
  publisher = {Association for Computational Linguistics},
  year = {2026},
  url = {https://arxiv.org/abs/2603.08501},
}

@article{Bhatia_2026,
  title={Advances in AI Systems on Islamic Knowledge Capabilities: A Critical Survey},
  publisher={Institute of Electrical and Electronics Engineers (IEEE)},
  author={Bhatia, Gagan and Mubarak, Hamdy and Hawasly, Majd and Jarrar, Mustafa and Mikros, George and Zaraket, Fadi and Alhirthani, Mahmoud and Al-Khatib, Mutaz and Cochrane, Logan and Darwish, Kareem and Yahiaoui, Rashid and Alam, Firoj},
  url={http://dx.doi.org/10.36227/techrxiv.177155997.77147487/v1},
  DOI={10.36227/techrxiv.177155997.77147487/v1},
  year={2026},
}

@article{ali2026menaspeechbankreferencevoicebank,
  title   = {{MENASpeechBank}: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs},
  author  = {Ali, Zien Sheikh and Bhatti, Hunzalah Hassan and Nandi, Rabindra Nath and Chowdhury, Shammur Absar and Alam, Firoj},
  journal = {arXiv preprint arXiv:2602.07036},
  year    = {2026},
  url     = {https://arxiv.org/abs/2602.07036},
}

@inproceedings{shahroor2026memelens,
  title = {{MemeLens}: Multilingual Multitask VLMs for Memes},
  author = {Shahroor, Ali Ezzat and Kmainasi, Mohamed Bayan and Hasnat, Abul and Dimitrov, Dimitar and Da San Martino, Giovanni and Nakov, Preslav and Alam, Firoj},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics},
  address = {San Diego, California, United States},
  publisher = {Association for Computational Linguistics},
  year = {2026},
  url = {https://arxiv.org/abs/2601.12539},
}

@article{bhatti2026harmonizingarabicaudiospace,
  title   = {Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic AudioLLMs},
  author  = {Bhatti, Hunzalah Hassan and Alam, Firoj and Chowdhury, Shammur Absar},
  journal = {arXiv preprint arXiv:2601.12494},
  year    = {2026},
  url     = {https://arxiv.org/abs/2601.12494},
}

@inproceedings{mousi2026counterfactualhallucination,
  title = {Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models},
  author = {Mousi, Basel and Dalvi, Fahim and Chowdhury, Shammur and Alam, Firoj and Durrani, Nadir},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics},
  address = {San Diego, California, United States},
  publisher = {Association for Computational Linguistics},
  year = {2026},
  url = {https://arxiv.org/abs/2602.05437},
}

@inproceedings{bhatia2026agenticrag,
  title = {From {RAG} to {Agentic RAG} for Faithful Islamic Question Answering},
  author = {Bhatia, Gagan and Mubarak, Hamdy and Jarrar, Mustafa and Mikros, George and Zaraket, Fadi and Alhirthani, Mahmoud and Al-Khatib, Mutaz and Cochrane, Logan and Darwish, Kareem and Yahiaoui, Rashid and Alam, Firoj},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics},
  address = {San Diego, California, United States},
  publisher = {Association for Computational Linguistics},
  year = {2026},
  url = {https://doi.org/10.48550/arXiv.2601.07528},
}

@article{alam2025everydaymmqa,
  title={{EverydayMMQA}: A Multilingual and Multimodal Framework for Culturally Grounded Spoken Visual QA},
author= {Alam, Firoj and Shahroor, Ali Ezzat and Hasan, Md. Arid and Ali, Zien Sheikh and Bhatti, Hunzalah Hassan and Kmainasi, Mohamed Bayan and Chowdhury, Shammur Absar and Mousi, Basel and Dalvi, Fahim and Durrani, Nadir and Milic-Frayling, Natasa},
  journal={arXiv preprint arXiv:2510.06371},
  year={2025}
}

@inproceedings{bhatti2025beyond,
  title={{Beyond MCQ}: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants},
  author={Bhatti, Hunzalah Hassan and Alam, Firoj},
  booktitle={The 15th edition of the Language Resources and Evaluation Conference (LREC 2026)},
  year={2026},
}

@article{abouzied2025combating,
  title={Combating Misinformation in the Arab World: Challenges and Opportunities},
  author={Abouzied, Azza and Alam, Firoj and Ali, Raian and Papotti, Paolo},
  journal={Communications of the ACM},
  volume={68},
  number={10},
  pages={48--53},
  year={2025},
  publisher={ACM New York, NY, USA}
}

@article{al2025landscape,
  title={The Landscape of Arabic Large Language Models},
  author={Al-Khalifa, Shahad and Durrani, Nadir and Al-Khalifa, Hend and Alam, Firoj},
  journal={Communications of the ACM},
  volume={68},
  number={10},
  pages={54--61},
  year={2025},
  publisher={ACM New York, NY, USA}
}

@inproceedings{kmainasi-etal-2025-memeintel,
    title = "{M}eme{I}ntel: Explainable Detection of Propagandistic and Hateful Memes",
    author = "Kmainasi, Mohamed Bayan  and
      Hasnat, Abul  and
      Hasan, Md Arid  and
      Shahroor, Ali Ezzat  and
      Alam, Firoj",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.1539/",
    doi = "10.18653/v1/2025.emnlp-main.1539",
    pages = "30251--30267",
    ISBN = "979-8-89176-332-6"
}

@inproceedings{bassi-etal-2025-annotating,
    title = "Annotating the Annotators: Analysis, Insights and Modelling from an Annotation Campaign on Persuasion Techniques Detection",
    author = "Bassi, Davide  and
      Dimitrov, Dimitar Iliyanov  and
      D{'}Auria, Bernardo  and
      Alam, Firoj  and
      Hasanain, Maram  and
      Moro, Christian  and
      Orr{\`u}, Luisa  and
      Turchi, Gian Piero  and
      Nakov, Preslav  and
      Da San Martino, Giovanni",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-acl.922/",
    doi = "10.18653/v1/2025.findings-acl.922",
    pages = "17918--17929",
    ISBN = "979-8-89176-256-5"
}
@inproceedings{hasanain-etal-2025-propxplain,
    title = "{P}rop{X}plain: Can {LLM}s Enable Explainable Propaganda Detection?",
    author = "Hasanain, Maram  and
      Hasan, Md Arid  and
      Kmainasi, Mohamed Bayan  and
      Sartori, Elisa  and
      Shahroor, Ali Ezzat  and
      Da San Martino, Giovanni  and
      Alam, Firoj",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.1296/",
    doi = "10.18653/v1/2025.findings-emnlp.1296",
    pages = "23855--23863",
    ISBN = "979-8-89176-335-7"
}

@inproceedings{hasan-etal-2025-nativqa,
    title = "{N}ativ{QA}: Multilingual Culturally-Aligned Natural Query for {LLM}s",
    author = "Hasan, Md. Arid  and
      Hasanain, Maram  and
      Ahmad, Fatema  and
      Laskar, Sahinur Rahman  and
      Upadhyay, Sunaya  and
      Sukhadia, Vrunda N  and
      Kutlu, Mucahid  and
      Chowdhury, Shammur Absar  and
      Alam, Firoj",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-acl.770/",
    doi = "10.18653/v1/2025.findings-acl.770",
    pages = "14886--14909",
    ISBN = "979-8-89176-256-5"
}

@inproceedings{hassan-bhatti-etal-2025-cultranai,
    title = "{C}ultran{AI} at {P}alm{X} 2025: Data Augmentation for Cultural Knowledge Representation",
    author = "Hassan Bhatti, Hunzalah  and
      Ahmed, Youssef  and
      Arid Hasan, Md  and
      Alam, Firoj",
    editor = "Darwish, Kareem  and
      Ali, Ahmed  and
      Abu Farha, Ibrahim  and
      Touileb, Samia  and
      Zitouni, Imed  and
      Abdelali, Ahmed  and
      Al-Ghamdi, Sharefah  and
      Alkhereyf, Sakhar  and
      Zaghouani, Wajdi  and
      Khalifa, Salam  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Hamed, Injy  and
      Alyafeai, Zaid  and
      Alowisheq, Areeb  and
      Inoue, Go  and
      Mrini, Khalil  and
      Alshammari, Waad",
    booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.arabicnlp-sharedtasks.111/",
    doi = "10.18653/v1/2025.arabicnlp-sharedtasks.111",
    pages = "809--817",
    ISBN = "979-8-89176-356-2"
}

@inproceedings{rafiul-biswas-etal-2025-marsadlab-palmx,
    title = "{M}arsad{L}ab at {P}alm{X} Shared Task: An {LLM} Benchmark for {A}rabic Culture and Islamic Civilization",
    author = "Rafiul Biswas, Md.  and
      Ibrahim, Shimaa  and
      Attia, Kais  and
      Alam, Firoj  and
      Zaghouani, Wajdi",
    editor = "Darwish, Kareem  and
      Ali, Ahmed  and
      Abu Farha, Ibrahim  and
      Touileb, Samia  and
      Zitouni, Imed  and
      Abdelali, Ahmed  and
      Al-Ghamdi, Sharefah  and
      Alkhereyf, Sakhar  and
      Zaghouani, Wajdi  and
      Khalifa, Salam  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Hamed, Injy  and
      Alyafeai, Zaid  and
      Alowisheq, Areeb  and
      Inoue, Go  and
      Mrini, Khalil  and
      Alshammari, Waad",
    booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.arabicnlp-sharedtasks.112/",
    doi = "10.18653/v1/2025.arabicnlp-sharedtasks.112",
    pages = "818--824",
    ISBN = "979-8-89176-356-2"
}

@inproceedings{tajrin-etal-2025-aya,
    title = "{AYA} at {P}alm{X} 2025: Modeling Cultural and Islamic Knowledge in {LLM}s",
    author = "Tajrin, Jannatul  and
      Ballav Roy, Bir  and
      Alam, Firoj",
    editor = "Darwish, Kareem  and
      Ali, Ahmed  and
      Abu Farha, Ibrahim  and
      Touileb, Samia  and
      Zitouni, Imed  and
      Abdelali, Ahmed  and
      Al-Ghamdi, Sharefah  and
      Alkhereyf, Sakhar  and
      Zaghouani, Wajdi  and
      Khalifa, Salam  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Hamed, Injy  and
      Alyafeai, Zaid  and
      Alowisheq, Areeb  and
      Inoue, Go  and
      Mrini, Khalil  and
      Alshammari, Waad",
    booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.arabicnlp-sharedtasks.114/",
    doi = "10.18653/v1/2025.arabicnlp-sharedtasks.114",
    pages = "830--836",
    ISBN = "979-8-89176-356-2"
}

@inproceedings{rafiul-biswas-etal-2025-marsadlab,
    title = "{M}arsad{L}ab at {A}ra{G}en{E}val Shared Task: {LLM}-Based Approaches to {A}rabic Authorship Style Transfer and Identification",
    author = "Rafiul Biswas, Md.  and
      Bessghaier, Mabrouka  and
      Alam, Firoj  and
      Zaghouani, Wajdi",
    editor = "Darwish, Kareem  and
      Ali, Ahmed  and
      Abu Farha, Ibrahim  and
      Touileb, Samia  and
      Zitouni, Imed  and
      Abdelali, Ahmed  and
      Al-Ghamdi, Sharefah  and
      Alkhereyf, Sakhar  and
      Zaghouani, Wajdi  and
      Khalifa, Salam  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Hamed, Injy  and
      Alyafeai, Zaid  and
      Alowisheq, Areeb  and
      Inoue, Go  and
      Mrini, Khalil  and
      Alshammari, Waad",
    booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.arabicnlp-sharedtasks.15/",
    doi = "10.18653/v1/2025.arabicnlp-sharedtasks.15",
    pages = "88--93",
    ISBN = "979-8-89176-356-2"
}

@inproceedings{zaghouani-etal-2025-mahed,
    title = "{MAHED} Shared Task: Multimodal Detection of Hope and Hate Emotions in {A}rabic Content",
    author = "Zaghouani, Wajdi  and
      Biswas, Md. Rafiul  and
      Bessghaier, Mabrouka  and
      Ibrahim, Shimaa  and
      Mikros, George  and
      Hasnat, Abul  and
      Alam, Firoj",
    editor = "Darwish, Kareem  and
      Ali, Ahmed  and
      Abu Farha, Ibrahim  and
      Touileb, Samia  and
      Zitouni, Imed  and
      Abdelali, Ahmed  and
      Al-Ghamdi, Sharefah  and
      Alkhereyf, Sakhar  and
      Zaghouani, Wajdi  and
      Khalifa, Salam  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Hamed, Injy  and
      Alyafeai, Zaid  and
      Alowisheq, Areeb  and
      Inoue, Go  and
      Mrini, Khalil  and
      Alshammari, Waad",
    booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.arabicnlp-sharedtasks.75/",
    doi = "10.18653/v1/2025.arabicnlp-sharedtasks.75",
    pages = "560--574",
    ISBN = "979-8-89176-356-2"
}


@inproceedings{almatham-etal-2025-balsam,
    title = "{BALSAM}: A Platform for Benchmarking {A}rabic Large Language Models",
    author = "Almatham, Rawan Nasser  and
      Darwish, Kareem Mohamed  and
      Al-Rasheed, Raghad  and
      Alshammari, Waad Thuwaini  and
      Alhoshan, Muneera  and
      Almazrua, Amal  and
      Al Wazrah, Asma  and
      Alheraki, Mais  and
      Alam, Firoj  and
      Nakov, Preslav  and
      Alzahrani, Norah A.  and
      Albilali, Eman  and
      Habash, Nizar  and
      El-Sheikh, Abdelrahman Mustafa  and
      Elmallah, Muhammad  and
      Mubarak, Hamdy  and
      Alyafeai, Zaid  and
      Anwar, Mohamed  and
      Li, Haonan  and
      Abdelali, Ahmed  and
      Altwairesh, Nora  and
      Hasanain, Maram  and
      Al-Thubaity, Abdulmohsen  and
      Shehata, Shady  and
      Alhafni, Bashar  and
      Hamed, Injy  and
      Inoue, Go  and
      Elmadani, Khalid N.  and
      Obeid, Ossama  and
      Haouari, Fatima  and
      Elsayed, Tamer  and
      Alghamdi, Emad A.  and
      Almubarak, Khalid  and
      Alshahrani, Saied  and
      Aljareh, Ola  and
      Alajlan, Safa  and
      Alshaqarawi, Areej  and
      Alshihri, Maryam  and
      Alghurabi, Sultana  and
      Alzeghayer, Atikah  and
      Altamimi, Afrah  and
      Alfaifi, Abdullah  and
      Alosaimy, Abdulrahman M",
    editor = "Darwish, Kareem  and
      Ali, Ahmed  and
      Abu Farha, Ibrahim  and
      Touileb, Samia  and
      Zitouni, Imed  and
      Abdelali, Ahmed  and
      Al-Ghamdi, Sharefah  and
      Alkhereyf, Sakhar  and
      Zaghouani, Wajdi  and
      Khalifa, Salam  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Hamed, Injy  and
      Alyafeai, Zaid  and
      Alowisheq, Areeb  and
      Inoue, Go  and
      Mrini, Khalil  and
      Alshammari, Waad",
    booktitle = "Proceedings of The Third Arabic Natural Language Processing Conference",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.arabicnlp-main.21/",
    doi = "10.18653/v1/2025.arabicnlp-main.21",
    pages = "258--277",
    ISBN = "979-8-89176-352-4"
}

@inproceedings{alam2025overview,
  title={Overview of the CLEF-2025 CheckThat! Lab: Subjectivity, fact-checking, claim normalization, and retrieval},
  author={Alam, Firoj and Stru{\ss}, Julia Maria and Chakraborty, Tanmoy and Dietze, Stefan and Hafid, Salim and Korre, Katerina and Muti, Arianna and Nakov, Preslav and Ruggeri, Federico and Schellhammer, Sebastian and others},
  booktitle={International Conference of the Cross-Language Evaluation Forum for European Languages},
  pages={199--223},
  year={2025},
  organization={Springer}
}

@inproceedings{alam2025clef,
  title={The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval},
  author={Alam, Firoj and Stru{\ss}, Julia Maria and Chakraborty, Tanmoy and Dietze, Stefan and Hafid, Salim and Korre, Katerina and Muti, Arianna and Nakov, Preslav and Ruggeri, Federico and Schellhammer, Sebastian and others},
  booktitle={European Conference on Information Retrieval},
  pages={467--478},
  year={2025},
  organization={Springer}
}




@inproceedings{Ersoy2025from,
  title={From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models},
  author={  Ersoy, Asim and Mousi, Basel Ahmad and Chowdhury, Shammur Absar and  Alam, Firoj and  Dalvi, Fahim I  and  Durrani, Nadir},
  booktitle = {{Proc. of the 26th Annual Conference of the International Speech Communication Association (INTERSPEECH)}},
  year={2025}
}


@inproceedings{Alam2025SpokenNativQA,
  title={SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs},
  author={Alam, Firoj and Hasan, Md Arid and Chowdhury, Shammur Absar},
  booktitle = {{Proc. of the 26th Annual Conference of the International Speech Communication Association (INTERSPEECH)}},
  year={2025}
}



@inproceedings{10.1145/3706598.3713150,
author = {Magdy, Walid and Mubarak, Hamdy and Salminen, Joni},
title = {Who should set the Standards? Analysing Censored Arabic Content on Facebook during the Palestine-Israel Conflict},
year = {2025},
isbn = {9798400713941},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3706598.3713150},
doi = {10.1145/3706598.3713150},
abstract = {Nascent research on human-computer interaction concerns itself with fairness of content moderation systems. Designing globally applicable content moderation systems requires considering historical, cultural, and socio-technical factors. Inspired by this line of work, we investigate Arab users’ perception of Facebook’s moderation practices. We collect a set of 448 deleted Arabic posts, and we ask Arab annotators to evaluate these posts based on (a) Facebook Community Standards (FBCS) and (b) their personal opinion. Each post was judged by 10 annotators to account for subjectivity. Our analysis shows a clear gap between the Arabs’ understanding of the FBCS and how Facebook implements these standards. The study highlights a need for discussion on the moderation guidelines on social media platforms about who decides the moderation guidelines, how these guidelines are interpreted, and how well they represent the views of marginalised user communities.},
booktitle = {Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems},
articleno = {178},
numpages = {16},
keywords = {Censorship, Content Moderation, Free Speech, Facebook, Social Media, Palestine Israel Conflict},
location = {
},
series = {CHI '25}
}


@inproceedings{yu-etal-2024-latent,
    title = "Latent Concept-based Explanation of {NLP} Models",
    author = "Yu, Xuemin  and
      Dalvi, Fahim  and
      Durrani, Nadir  and
      Nouri, Marzia  and
      Sajjad, Hassan",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.692/",
    doi = "10.18653/v1/2024.emnlp-main.692",
    pages = "12435--12459",
    abstract = "Interpreting and understanding the predictions made by deep learning models poses a formidable challenge due to their inherently opaque nature. Many previous efforts aimed at explaining these predictions rely on input features, specifically, the words within NLP models. However, such explanations are often less informative due to the discrete nature of these words and their lack of contextual verbosity. To address this limitation, we introduce the Latent Concept Attribution method (LACOAT), which generates explanations for predictions based on latent concepts. Our foundational intuition is that a word can exhibit multiple facets, contingent upon the context in which it is used. Therefore, given a word in context, the latent space derived from our training process reflects a specific facet of that word. LACOAT functions by mapping the representations of salient input words into the training latent space, allowing it to provide latent context-based explanations of the prediction."
}


@inproceedings{hasanain-etal-2024-large,
    title = "Large Language Models for Propaganda Span Annotation",
    author = "Hasanain, Maram  and
      Ahmad, Fatema  and
      Alam, Firoj",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.850/",
    doi = "10.18653/v1/2024.findings-emnlp.850",
    pages = "14522--14532",
    abstract = "The use of propagandistic techniques in online content has increased in recent years aiming to manipulate online audiences. Fine-grained propaganda detection and extraction of textual spans where propaganda techniques are used, are essential for more informed content consumption. Automatic systems targeting the task over lower resourced languages are limited, usually obstructed by lack of large scale training datasets. Our study investigates whether Large Language Models (LLMs), such as GPT-4, can effectively extract propagandistic spans. We further study the potential of employing the model to collect more cost-effective annotations. Finally, we examine the effectiveness of labels provided by GPT-4 in training smaller language models for the task. The experiments are performed over a large-scale in-house manually annotated dataset. The results suggest that providing more annotation context to GPT-4 within prompts improves its performance compared to human annotators. Moreover, when serving as an expert annotator (consolidator), the model provides labels that have higher agreement with expert annotators, and lead to specialized models that achieve state-of-the-art over an unseen Arabic testing set. Finally, our work is the first to show the potential of utilizing LLMs to develop annotated datasets for propagandistic spans detection task prompting it with annotations from human annotators with limited expertise. All scripts and annotations will be shared with the community."
}


@inproceedings{abdaljalil-mubarak-2024-wikidata,
    title = "{W}ikidata as a Source of Demographic Information",
    author = "Abdaljalil, Samir  and
      Mubarak, Hamdy",
    editor = "Habash, Nizar  and
      Bouamor, Houda  and
      Eskander, Ramy  and
      Tomeh, Nadi  and
      Abu Farha, Ibrahim  and
      Abdelali, Ahmed  and
      Touileb, Samia  and
      Hamed, Injy  and
      Onaizan, Yaser  and
      Alhafni, Bashar  and
      Antoun, Wissam  and
      Khalifa, Salam  and
      Haddad, Hatem  and
      Zitouni, Imed  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Mrini, Khalil",
    booktitle = "Proceedings of the Second Arabic Natural Language Processing Conference",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.arabicnlp-1.1/",
    doi = "10.18653/v1/2024.arabicnlp-1.1",
    pages = "1--10",
    abstract = "Names carry important information about our identities and demographics such as gender, nationality, ethnicity, etc. We investigate the use of individual{'}s name, in both Arabic and English, to predict important attributes, namely country, region, gender, and language. We extract data from Wikidata, and normalize it, to build a comprehensive dataset consisting of more than 1 million entities and their normalized attributes. We experiment with a Linear SVM approach, as well as two Transformers approaches consisting of BERT model fine-tuning and Transformers pipeline. Our results indicate that we can predict the gender, language and region using the name only with a confidence over 0.65. The country attribute can be predicted with less accuracy. The Linear SVM approach outperforms the other approaches for all the attributes. The best performing approach was also evaluated on another dataset that consists of 1,500 names from 15 countries (covering different regions) extracted from Twitter, and yields similar results."
}


@inproceedings{fadeeva-etal-2024-fact,
    title = "Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification",
    author = "Fadeeva, Ekaterina  and
      Rubashevskii, Aleksandr  and
      Shelmanov, Artem  and
      Petrakov, Sergey  and
      Li, Haonan  and
      Mubarak, Hamdy  and
      Tsymbalov, Evgenii  and
      Kuzmin, Gleb  and
      Panchenko, Alexander  and
      Baldwin, Timothy  and
      Nakov, Preslav  and
      Panov, Maxim",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-acl.558/",
    doi = "10.18653/v1/2024.findings-acl.558",
    pages = "9367--9385",
    abstract = "Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of the output being generally factually correct, making it extremely hard for the users to spot them. Current services that leverage LLMs usually do not provide any means for detecting unreliable generations. Here, we aim to bridge this gap. In particular, we propose a novel fact-checking and hallucination detection pipeline based on token-level uncertainty quantification. Uncertainty scores leverage information encapsulated in the output of a neural network or its layers to detect unreliable predictions, and we show that they can be used to fact-check the atomic claims in the LLM output. Moreover, we present a novel token-level uncertainty quantification method that removes the impact of uncertainty about what claim to generate on the current step and what surface form to use. Our method Claim Conditioned Probability (CCP) measures only the uncertainty of a particular claim value expressed by the model. Experiments on the task of biography generation demonstrate strong improvements for CCP compared to the baselines for seven different LLMs and four languages. Human evaluation reveals that the fact-checking pipeline based on uncertainty quantification is competitive with a fact-checking tool that leverages external knowledge."
}

@inproceedings{zaghouani-etal-2024-hateful,
    title = "So Hateful! Building a Multi-Label Hate Speech Annotated {A}rabic Dataset",
    author = "Zaghouani, Wajdi  and
      Mubarak, Hamdy  and
      Biswas, Md. Rafiul",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.1308/",
    pages = "15044--15055",
    abstract = "Social media enables widespread propagation of hate speech targeting groups based on ethnicity, religion, or other characteristics. With manual content moderation being infeasible given the volume, automatic hate speech detection is essential. This paper analyzes 70,000 Arabic tweets, from which 15,965 tweets were selected and annotated, to identify hate speech patterns and train classification models. Annotators labeled the Arabic tweets for offensive content, hate speech, emotion intensity and type, effect on readers, humor, factuality, and spam. Key findings reveal 15{\%} of tweets contain offensive language while 6{\%} have hate speech, mostly targeted towards groups with common ideological or political affiliations. Annotations capture diverse emotions, and sarcasm is more prevalent than humor. Additionally, 10{\%} of tweets provide verifiable factual claims, and 7{\%} are deemed important. For hate speech detection, deep learning models like AraBERT outperform classical machine learning approaches. By providing insights into hate speech characteristics, this work enables improved content moderation and reduced exposure to online hate. The annotated dataset advances Arabic natural language processing research and resources."
}

@inproceedings{mubarak-etal-2024-halwasa,
    title = "Halwasa: Quantify and Analyze Hallucinations in Large Language Models: {A}rabic as a Case Study",
    author = "Mubarak, Hamdy  and
      Al-Khalifa, Hend  and
      Alkhalefah, Khaloud Suliman",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.705/",
    pages = "8008--8015",
    abstract = "Large Language Models (LLMs) have shown superb abilities to generate texts that are indistinguishable from human-generated texts in many cases. However, sometimes they generate false, incorrect, or misleading content, which is often described as {\textquotedblleft}hallucinations{\textquotedblright}. Quantifying and analyzing hallucination in LLMs can increase their reliability and usage. While hallucination is being actively studied for English and other languages, and different benchmarking datsets have been created, this area is not studied at all for Arabic. In our paper, we create the first Arabic dataset that contains 10K of generated sentences by LLMs and annotate it for factuality and correctness. We provide detailed analysis of the dataset to analyze factual and linguistic errors. We found that 25{\%} of the generated sentences are factually incorrect. We share the dataset with the research community."
}


>>>>>>> upstream/master
@inproceedings{ThatiAR2025,
  title     = {{ThatiAR}: Subjectivity Detection in Arabic News Sentences},
  author    = {Reem Suwaileh and Maram Hasanain and Fatema Hubail and Wajdi Zaghouani and Firoj Alam},
  booktitle = {Proceedings of the International AAAI Conference on Web and Social Media (ICWSM 2025)},
  year      = {2025},
  address   = {Copenhagen, Denmark},
  month     = jun,
}

@inproceedings{kmainasi-etal-2025-llamalens,
    title = "{L}lama{L}ens: Specialized Multilingual {LLM} for Analyzing News and Social Media Content",
    author = "Kmainasi, Mohamed Bayan  and
      Shahroor, Ali Ezzat  and
      Hasanain, Maram  and
      Laskar, Sahinur Rahman  and
      Hassan, Naeemul  and
      Alam, Firoj",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-naacl.313/",
    pages = "5627--5649",
    ISBN = "979-8-89176-195-7",
}
@inproceedings{basher-etal-2025-bntts,
    title = "{B}n{TTS}: Few-Shot Speaker Adaptation in Low-Resource Setting",
    author = "Basher, Mohammad Jahid Ibna  and
      Kowsher, Md  and
      Islam, Md Saiful  and
      Nandi, Rabindra Nath  and
      Prottasha, Nusrat Jahan  and
      Menon, Mehadi Hasan  and
      Muntasir, Tareq Al  and
      Chowdhury, Shammur Absar  and
      Alam, Firoj  and
      Yousefi, Niloofar  and
      Garibay, Ozlem",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-naacl.279/",
    pages = "4956--4968",
    ISBN = "979-8-89176-195-7",
}

@InProceedings{10.1007/978-3-031-88720-8_68,
author="Alam, Firoj
and Stru{\ss}, Julia Maria
and Chakraborty, Tanmoy
and Dietze, Stefan
and Hafid, Salim
and Korre, Katerina
and Muti, Arianna
and Nakov, Preslav
and Ruggeri, Federico
and Schellhammer, Sebastian
and Setty, Vinay
and Sundriyal, Megha
and Todorov, Konstantin
and V., Venktesh",
editor="Hauff, Claudia
and Macdonald, Craig
and Jannach, Dietmar
and Kazai, Gabriella
and Nardini, Franco Maria
and Pinelli, Fabio
and Silvestri, Fabrizio
and Tonellotto, Nicola",
title="The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval",
booktitle="Advances in Information Retrieval",
year="2025",
publisher="Springer Nature Switzerland",
address="Cham",
pages="467--478",
isbn="978-3-031-88720-8",
}

@inproceedings{mousi-etal-2025-aradice,
    title = "{A}ra{D}i{CE}: Benchmarks for Dialectal and Cultural Capabilities in {LLM}s",
    author = "Mousi, Basel  and
      Durrani, Nadir  and
      Ahmad, Fatema  and
      Hasan, Md. Arid  and
      Hasanain, Maram  and
      Kabbani, Tameem  and
      Dalvi, Fahim  and
      Chowdhury, Shammur Absar  and
      Alam, Firoj",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.coling-main.283/",
    pages = "4186--4218",
}


@inproceedings{chowdhury-etal-2025-genai,
    title = "{G}en{AI} Content Detection Task 2: {AI} vs. Human {--} Academic Essay Authenticity Challenge",
    author = "Chowdhury, Shammur Absar  and
      Almerekhi, Hind  and
      Kutlu, Mucahid  and
      Kele{\c{s}}, Kaan Efe  and
      Ahmad, Fatema  and
      Mohiuddin, Tasnim  and
      Mikros, George  and
      Alam, Firoj",
    editor = "Alam, Firoj  and
      Nakov, Preslav  and
      Habash, Nizar  and
      Gurevych, Iryna  and
      Chowdhury, Shammur  and
      Shelmanov, Artem  and
      Wang, Yuxia  and
      Artemova, Ekaterina  and
      Kutlu, Mucahid  and
      Mikros, George",
    booktitle = "Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "International Conference on Computational Linguistics",
    url = "https://aclanthology.org/2025.genaidetect-1.37/",
    pages = "323--333",
}
@inproceedings{dugan-etal-2025-genai,
    title = "{G}en{AI} Content Detection Task 3: Cross-Domain Machine Generated Text Detection Challenge",
    author = "Dugan, Liam  and
      Zhu, Andrew  and
      Alam, Firoj  and
      Nakov, Preslav  and
      Apidianaki, Marianna  and
      Callison-Burch, Chris",
    editor = "Alam, Firoj  and
      Nakov, Preslav  and
      Habash, Nizar  and
      Gurevych, Iryna  and
      Chowdhury, Shammur  and
      Shelmanov, Artem  and
      Wang, Yuxia  and
      Artemova, Ekaterina  and
      Kutlu, Mucahid  and
      Mikros, George",
    booktitle = "Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "International Conference on Computational Linguistics",
    url = "https://aclanthology.org/2025.genaidetect-1.45/",
    pages = "377--388",
}

@proceedings{genaidetect-ws-2025-1,
    title = "Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)",
    editor = "Alam, Firoj  and
      Nakov, Preslav  and
      Habash, Nizar  and
      Gurevych, Iryna  and
      Chowdhury, Shammur  and
      Shelmanov, Artem  and
      Wang, Yuxia  and
      Artemova, Ekaterina  and
      Kutlu, Mucahid  and
      Mikros, George",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "International Conference on Computational Linguistics",
    url = "https://aclanthology.org/2025.genaidetect-1.0/"
}

@inproceedings{vrunda2024,
  title={Children’s Speech Recognition through Discrete Token Enhancement},
  author={Sukhadia, Vrunda N. and Chowdhury, Shammur Absar },
  booktitle = {{Proc. of the 25th Annual Conference of the International Speech Communication Association (INTERSPEECH)}},
  year={2024}
}

@inproceedings{ElKheir2024Beyond,
  title={Beyond Orthography: Automatic Recovery of Short Vowels and Dialectal Sounds in Arabic},
  author={Yassine El Kheir and Hamdy Mubarak and Ahmed Ali and Shammur Absar Chowdhury},
  booktitle={Proc. of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL)},
  year={2024}
}

@inproceedings{el2024l1,
  title={L1-aware multilingual mispronunciation detection framework},
  author={El Kheir, Yassine and Chowdhury, Shammur Absar and Ali, Ahmed},
  booktitle={Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={12752--12756},
  year={2024},
  organization={IEEE}
}
@inproceedings{el2024speech,
  title={Speech representation analysis based on inter-and intra-model similarities},
  author={El Kheir, Yassine and Ali, Ahmed and Chowdhury, Shammur Absar},
  booktitle={2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)},
  pages={848--852},
  year={2024},
  organization={IEEE}
}

@inproceedings{hussein2024speech,
  title={Speech collage: code-switched audio generation by collaging monolingual corpora},
  author={Hussein, Amir and Zeinali, Dorsa and Klejch, Ond{\v{r}}ej and Wiesner, Matthew and Yan, Brian and Chowdhury, Shammur and Ali, Ahmed and Watanabe, Shinji and Khudanpur, Sanjeev},
  booktitle={Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={12006--12010},
  year={2024},
  organization={IEEE}
}


@inproceedings{kheir2023automatic,
  title={Automatic Pronunciation Assessment-A Review},
  author={Kheir, Yassine and Ali, Ahmed and Chowdhury, Shammur},
  booktitle={Proc. of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  pages={8304--8324},
  year={2023}
}

@inproceedings{speechBlender2023,
  author    = {Yassine El Kheir and Shammur Absar Chowdhury and Ahmed Ali},
  title     = {Speechblender: Speech augmentation framework for mispronunciation data generation},
  booktitle = {Proc. of the Speech and Language Technology in Education (SLaTE)},
  year      = {2023}
}

@inproceedings{multiview2023,
  author    = {Yassine El Kheir and Shammur Absar Chowdhury and Ahmed Ali},
  title     = {Multi-View Multi-Task Representation Learning for Mispronunciation Detection},
  booktitle = {Proc. of the Speech and Language Technology in Education (SLaTE)},
  year      = {2023}
}

@article{chowdhury2023end,
  title={What do end-to-end speech models learn about speaker, language and channel information? a layer-wise and neuron-level analysis},
  author={Chowdhury, Shammur Absar and Durrani, Nadir and Ali, Ahmed},
  journal={Computer Speech \& Language},
  volume={83},
  pages={101539},
  year={2023},
  publisher={Elsevier}
}


@inproceedings{hamed2023benchmarking,
  title={Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition},
  author={Hamed, Injy and Hussein, Amir and Chellah, Oumnia and Chowdhury, Shammur and Mubarak, Hamdy and Sitaram, Sunayana and Habash, Nizar and Ali, Ahmed},
  booktitle={Proc. of the 2022 IEEE Spoken Language Technology Workshop (SLT)},
  pages={999--1005},
  year={2022},
  organization={IEEE}
}

@inproceedings{hussein2023textual,
  title={Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition},
  author={Hussein, Amir and Chowdhury, Shammur Absar and Abdelali, Ahmed and Dehak, Najim and Ali, Ahmed and Khudanpur, Sanjeev},
  booktitle={Proc. of the 2022 IEEE Spoken Language Technology Workshop (SLT)},
  pages={777--784},
  year={2022},
  organization={IEEE}
}

@inproceedings{chowdhury2023multilingual,
  title={MULTILINGUAL WORD ERROR RATE ESTIMATION: E-WER3},
  author={Chowdhury, Shammur Absar and Ali, Ahmed},
  booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2023}
}
@inproceedings{kheir2023qvoice,
  title={QVoice: Arabic Speech Pronunciation Learning Application},
  author={Kheir, Yassine El and Khnaisser, Fouad and Chowdhury, Shammur Absar and Mubarak, Hamdy and Afzal, Shazia and Ali, Ahmed},
  booktitle={INTERSPEECH},
  year={2023}
}
@inproceedings{elshahawy2023myvoice,
  title={MyVoice: Arabic Speech Resource Collaboration Platform},
  author={Elshahawy, Yousseif and Kheir, Yassine El and Chowdhury, Shammur Absar and Ali, Ahmed},
  booktitle={INTERSPEECH},
  year={2023}
}

@inproceedings{hamed2022benchmarking,
  title={Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition},
  author={Hamed, Injy and Hussein, Amir and Chellah, Oumnia and Chowdhury, Shammur and Mubarak, Hamdy and Sitaram, Sunayana and Habash, Nizar and Ali, Ahmed},
  booktitle={2022 IEEE Spoken Language Technology Workshop (SLT)},
  year={2022}
}

@inproceedings{zamparelli2022semeval,
  title={SemEval-2022 Task 3: PreTENS-Evaluating Neural Networks on Presuppositional Semantic Knowledge},
  author={Zamparelli, Roberto and Chowdhury, Shammur and Brunato, Dominique and Chesi, Cristiano and Dell’Orletta, Felice and Hasan, Md Arid and Venturi, Giulia},
  booktitle={Proc. of the 16th International Workshop on Semantic Evaluation (SemEval-2022)},
  pages={228--238},
  year={2022}
}

@inproceedings{bayerl2022can,
  title={What can Speech and Language Tell us About the Working Alliance in Psychotherapy},
  author={Bayerl, Sebastian P and Roccabruna, Gabriel and Chowdhury, Shammur Absar and Ciulli, Tommaso and Danieli, Morena and Riedhammer, Korbinian and Riccardi, Giuseppe},
  booktitle = {{{{Proc. of the 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH)}}}},
  year={2022}
}

@article{mubarak2022emojis,
  title={Emojis as anchors to detect arabic offensive language and hate speech},
  author={Mubarak, Hamdy and Hassan, Sabit and Chowdhury, Shammur Absar},
  journal={Natural Language Engineering (NLE) Journal},
  year={2022}
}
@article{jansen2021persona,
  title={Persona analytics: Analyzing the stability of online segments and content interests over time using non-negative matrix factorization},
  author={Jansen, Bernard J and Jung, Soon-gyo and Chowdhury, Shammur A and Salminen, Joni},
  journal={Expert Systems with Applications},
  volume={185},
  pages={115611},
  year={2021},
  publisher={Pergamon}
}

@article{ali_connecting_2021,
	title = {Connecting {Arabs}: bridging the gap in dialectal speech recognition},
	volume = {64},
	number = {4},
	journal = {Communications of the ACM},
	author = {Ali, Ahmed and Chowdhury, Shammur and Afify, Mohamed and El-Hajj, Wassim and Hajj, Hazem and Abbas, Mourad and Hussein, Amir and Ghneim, Nada and Abushariah, Mohammad and Alqudah, Assal},
	year = {2021},
	note = {Publisher: ACM New York, NY, USA},
	pages = {124--129},
}

@inproceedings{chowdhury_towards_2021,
	title = {Towards {One} {Model} to {Rule} {All}: {Multilingual} {Strategy} for {Dialectal} {Code}-{Switching} {Arabic} {ASR}},
	booktitle = {{{{Proc. of the 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH)}}}},
	author = {Chowdhury, Shammur Absar and Hussein, Amir and Abdelali, Ahmed and Ali, Ahmed},
	year = {2021}
}

@inproceedings{ali_arabic_2021,
	title = {Arabic {Code}-{Switching} {Speech} {Recognition} using {Monolingual} {Data}},
	booktitle = {{{{Proc. of the 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH)}}}},
	author = {Ali, Ahmed and Chowdhury, Shammur and Hussein, Amir and Yasser, Hifny},
	year = {2021},
}

@inproceedings{mubarak_qasr_2021,
	title = {{QASR}: {QCRI} {Aljazeera} {Speech} {Resource}. {A} {Large} {Scale} {Annotated} {Arabic} {Speech} {Corpus}},
	booktitle = {{Proc. of the 59th Annual Meeting of the Association for Computational Linguistics (ACL)}},
	author = {Mubarak, Hamdy and Hussein, Amir and Chowdhury, Shammur Absar and Ali, Ahmed},
	year = {2021},
}
@article{islam2024datanarrative,
  title={{D}ata{N}arrative: Automated Data-Driven Storytelling with Visualizations and Texts},
  author={Islam, Mohammed Saidul and Hoque, Enamul and Joty, Shafiq and Laskar, Md Tahmid Rahman and Parvez, Md Rizwan},
  journal={arXiv preprint arXiv:2408.05346},
  year={2024}
}

@article{laskar2024systematic,
  title={A systematic survey and critical review on evaluating large language models: Challenges, limitations, and recommendations},
  author={Laskar, Md Tahmid Rahman and Alqahtani, Sawsan and Bari, M Saiful and Rahman, Mizanur and Khan, Mohammad Abdullah Matin and Khan, Haidar and Jahan, Israt and Bhuiyan, Amran and Tan, Chee Wei and Parvez, Md Rizwan and others},
  journal={arXiv preprint arXiv:2407.04069},
  year={2024}
}

@article{islam2024open,
  title={{OPEN}-{RAG}: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models},
  author={Islam, Shayekh Bin and Rahman, Md Asib and Hossain, KSM and Hoque, Enamul and Joty, Shafiq and Parvez, Md Rizwan},
  journal={arXiv preprint arXiv:2410.01782},
  year={2024}
}

@inproceedings{masry-etal-2024-chartinstruct,
    title = "{C}hart{I}nstruct: Instruction Tuning for Chart Comprehension and Reasoning",
    author = "Masry, Ahmed  and
      Shahmohammadi, Mehrad  and
      Parvez, Md Rizwan  and
      Hoque, Enamul  and
      Joty, Shafiq",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand and virtual meeting",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-acl.619",
    doi = "10.18653/v1/2024.findings-acl.619",
    pages = "10387--10409",
    abstract = "Charts provide visual representations of data and are widely used for analyzing information, addressing queries, and conveying insights to others. Various chart-related downstream tasks have emerged recently, such as question-answering and summarization. A common strategy to solve these tasks is to fine-tune various models originally trained on vision tasks language. However, such task-specific models are not capable of solving a wide range of chart-related tasks, constraining their real-world applicability. To overcome these challenges, we introduce ChartInsruct: a novel chart-specific vision-language Instruction-following dataset comprising 191K instructions generated with 71K charts. We then present two distinct systems for instruction tuning on such datasets: (1) an end-to-end model that connects a vision encoder for chart understanding with a LLM; and (2) a pipeline model that employs a two-step approach to extract chart data tables and input them into the LLM. In experiments on four downstream tasks, we first show the effectiveness of our model{--}achieving a new set of state-of-the-art results. Further evaluation shows that our instruction-tuning approach supports a wide array of real-world chart comprehension and reasoning scenarios, thereby expanding the scope and applicability of our models to new kinds of tasks.",
}


@inproceedings{islam-etal-2024-mapcoder,
    title = "{M}ap{C}oder: Multi-Agent Code Generation for Competitive Problem Solving",
    author = "Islam, Md. Ashraful  and
      Ali, Mohammed Eunus  and
      Parvez, Md Rizwan",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-long.269",
    doi = "10.18653/v1/2024.acl-long.269",
    pages = "4912--4944",
    abstract = "Code synthesis, which requires a deep understanding of complex natural language (NL) problem descriptions, generation of code instructions for complex algorithms and data structures, and the successful execution of comprehensive unit tests, presents a significant challenge. Thus, while large language models (LLMs) demonstrate impressive proficiency in natural language processing (NLP), their performance in code generation tasks remains limited. In this paper, we introduce a new approach to code generation tasks leveraging the multi-agent prompting that uniquely replicates the full cycle of program synthesis as observed in human developers. Our framework, MapCoder, consists of four LLM agents specifically designed to emulate the stages of this cycle: recalling relevant examples, planning, code generation, and debugging. After conducting thorough experiments, with multiple LLMs ablations and analyses across eight challenging competitive problem-solving and program synthesis benchmarks{---}MapCoder showcases remarkable code generation capabilities, achieving their new state-of-the-art (pass@1) results{---}(HumanEval 93.9{\%}, MBPP 83.1{\%}, APPS 22.0{\%}, CodeContests 28.5{\%}, and xCodeEval 45.3{\%}). Moreover, our method consistently delivers superior performance across various programming languages and varying problem difficulties. We open-source our framework at https://github.com/Md-Ashraful-Pramanik/MapCoder.",
}


@inproceedings{boughorbel-etal-2024-improving,
    title = "Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis",
    author = "Boughorbel, Sabri  and
      Parvez, Md Rizwan  and
      Hawasly, Majd",
    editor = "Habash, Nizar  and
      Bouamor, Houda  and
      Eskander, Ramy  and
      Tomeh, Nadi  and
      Abu Farha, Ibrahim  and
      Abdelali, Ahmed  and
      Touileb, Samia  and
      Hamed, Injy  and
      Onaizan, Yaser  and
      Alhafni, Bashar  and
      Antoun, Wissam  and
      Khalifa, Salam  and
      Haddad, Hatem  and
      Zitouni, Imed  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Mrini, Khalil",
    booktitle = "Proceedings of The Second Arabic Natural Language Processing Conference",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.arabicnlp-1.7",
    doi = "10.18653/v1/2024.arabicnlp-1.7",
    pages = "73--88",
    abstract = "Training LLMs in low resources languages usually utilizes machine translation (MT) data augmentation from English language. However, translation brings a number of challenges: there are large costs attached to translating and curating huge amounts of content with high-end machine translation solutions; the translated content carries over cultural biases; and if the translation is not faithful and accurate, the quality of the data degrades causing issues in the trained model. In this work, we investigate the role of translation and synthetic data in training language models. We translate TinyStories, a dataset of 2.2M short stories for 3-4 year old children, from English to Arabic using the open NLLB-3B MT model. We train a number of story generation models of size 1M-33M parameters using this data. We identify a number of quality and task-specific issues in the resulting models. To rectify these issues, we further pre-train the models with a small dataset of synthesized high-quality stories generated by a capable LLM in Arabic, representing 1{\%} of the original training data. We show, using GPT-4 as a judge and dictionary learning analysis from mechanistic interpretability, that the suggested approach is a practical means to resolve some of the translation pitfalls. We illustrate the improvement through case studies of linguistic and cultural bias issues.",
}


@inproceedings{hawasly2024scaling,
  title={Scaling up Discovery of Latent Concepts in Deep NLP Models},
  author={Hawasly, Majd and Dalvi, Fahim and Durrani, Nadir},
  booktitle={Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages={793--806},
  year={2024}
}

@inproceedings{boughorbel2023analyzing,
  title={Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic},
  author={Boughorbel, Sabri and Hawasly, Majd},
  booktitle={Proceedings of ArabicNLP 2023},
  pages={128--139},
  year={2023}
}

@inproceedings{khan-etal-2024-xcodeeval,
    title = "{XC}ode{E}val: An Execution-based Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval",
    author = "Khan, Mohammad Abdullah Matin  and
      Bari, M Saiful  and
      Long, Do  and
      Wang, Weishi  and
      Parvez, Md Rizwan  and
      Joty, Shafiq",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-long.367",
    doi = "10.18653/v1/2024.acl-long.367",
    pages = "6766--6805",
    abstract = "Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments. However, the evaluation of these models has often been performed in a scattered way on only one or two specific tasks, in a few languages, at a partial granularity (e.g., function) level, and in many cases without proper training data. Even more concerning is that in most cases the evaluation of generated codes has been done in terms of mere lexical overlap with a reference code rather than actual execution. We introduce *xCodeEval*, the largest executable multilingual multitask benchmark to date consisting of 25 M document-level coding examples (16.5 B tokens) from about 7.5 K unique problems covering up to 11 programming languages with execution-level parallelism. It features a total of 7 tasks involving code understanding, generation, translation and retrieval. *xCodeEval* adopts an execution-based evaluation and offers a multilingual code execution engine, *ExecEval* that supports unit test based execution in all the 11 languages. To address the challenge of balancing the distributions of text-code samples over multiple attributes in validation/test sets, we propose a novel data splitting and a data selection schema based on the geometric mean and graph-theoretic principle. Our experiments with OpenAI{'}s LLMs (zero-shot) and open-LLMs (zero-shot and fine-tuned) on the tasks and languages demonstrate to be quite challenging as per the current advancements in language models.",
}

@article{mousi2024aradicebenchmarksdialectalcultural,
    title={{AraDiCE}: Benchmarks for Dialectal and Cultural Capabilities in LLMs},
    author={Basel Mousi and Nadir Durrani and Fatema Ahmad and Md. Arid Hasan and Maram Hasanain and Tameem Kabbani and Fahim Dalvi and Shammur Absar Chowdhury and Firoj Alam},
    year={2024},
    journal={arXiv preprint arXiv:2409.11404},
    archivePrefix={arXiv},
    eprint={2409.11404},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2409.11404},
}

@inproceedings{kmainasi2024nativevsnonnativelanguage,
      title={Native vs Non-Native Language Prompting: A Comparative Analysis},
      booktitle = {Proceedings of The 25th International Web Information Systems Engineering Conference (WISE)},
      year = {2024},
      address = {Doha, Qatar},
      url={https://arxiv.org/abs/2409.07054},
}

@inproceedings{alam2024propagandahatemultimodalanalysis,
      title={Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMs},
      author={Firoj Alam and Md. Rafiul Biswas and Uzair Shah and Wajdi Zaghouani and Georgios Mikros},
      booktitle = {Proceedings of The 25th International Web Information Systems Engineering Conference (WISE)},
      year = {2024},
      address = {Doha, Qatar},
      url={https://arxiv.org/abs/2409.07246},
}



@inproceedings{alam-etal-2024-armeme,
    title = "{A}r{M}eme: Propagandistic Content in {A}rabic Memes",
    author = "Alam, Firoj  and
      Hasnat, Abul  and
      Ahmad, Fatema  and
      Hasan, Md. Arid  and
      Hasanain, Maram",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.1173/",
    doi = "10.18653/v1/2024.emnlp-main.1173",
    pages = "21071--21090"
}



@inproceedings{hasanain-etal-2024-araieval,
    title = "{A}r{AIE}val Shared Task: Propagandistic Techniques Detection in Unimodal and Multimodal {A}rabic Content",
    author = "Hasanain, Maram  and
      Hasan, Md. Arid  and
      Ahmad, Fatema  and
      Suwaileh, Reem  and
      Biswas, Md. Rafiul  and
      Zaghouani, Wajdi  and
      Alam, Firoj",
    editor = "Habash, Nizar  and
      Bouamor, Houda  and
      Eskander, Ramy  and
      Tomeh, Nadi  and
      Abu Farha, Ibrahim  and
      Abdelali, Ahmed  and
      Touileb, Samia  and
      Hamed, Injy  and
      Onaizan, Yaser  and
      Alhafni, Bashar  and
      Antoun, Wissam  and
      Khalifa, Salam  and
      Haddad, Hatem  and
      Zitouni, Imed  and
      AlKhamissi, Badr  and
      Almatham, Rawan  and
      Mrini, Khalil",
    booktitle = "Proceedings of The Second Arabic Natural Language Processing Conference",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.arabicnlp-1.44",
    pages = "456--466",
    abstract = "We present an overview of the second edition of the ArAIEval shared task, organized as part of the ArabicNLP 2024 conference co-located with ACL 2024. In this edition, ArAIEval offers two tasks: (i) detection of propagandistic textual spans with persuasion techniques identification in tweets and news articles, and (ii) distinguishing between propagandistic and non-propagandistic memes. A total of 14 teams participated in the final evaluation phase, with 6 and 9 teams participating in Tasks 1 and 2, respectively. Finally, 11 teams submitted system description papers. Across both tasks, we observed that fine-tuning transformer models such as AraBERT was at the core of the majority of the participating systems. We provide a description of the task setup, including a description of the dataset construction and the evaluation setup. We further provide a brief overview of the participating systems. All datasets and evaluation scripts are released to the research community. We hope this will enable further research on these important tasks in Arabic.",
}
@InProceedings{CheckThat:ECIR2024,
    author="Barr{\'o}n-Cede{\~{n}}o, Alberto
        and Alam, Firoj
        and Chakraborty, Tanmoy
        and Elsayed, Tamer
        and Nakov, Preslav
        and Przyby{\l}a, Piotr
        and Stru{\ss}, Julia Maria
        and Haouari, Fatima
        and Hasanain, Maram
        and Ruggeri, Federico
        and Song, Xingyi
        and Suwaileh, Reem",
    editor="Goharian, Nazli
        and Tonellotto, Nicola
        and He, Yulan
        and Lipani, Aldo
        and McDonald, Graham
        and Macdonald, Craig
        and Ounis, Iadh",
    title="The {CLEF}-2024 {C}heck{T}hat! {L}ab: Check-Worthiness, Subjectivity, Persuasion, Roles, Authorities, and Adversarial Robustness",
    booktitle="Advances in Information Retrieval",
    year="2024",
    publisher="Springer Nature Switzerland",
    NOaddress="Cham",
    pages="449--458",
    abstract="The first five editions of the CheckThat! lab focused on the main tasks of the information verification pipeline: check-worthiness, evidence retrieval and pairing, and verification. Since the 2023 edition, it has been focusing on new problems that can support the research and decision making during the verification process. In this new edition, we focus on new problems and ---for the first time--- we propose six tasks in fifteen languages (Arabic, Bulgarian, English, Dutch, French, Georgian, German, Greek, Italian, Polish, Portuguese, Russian, Slovene, Spanish, and code-mixed Hindi-English): Task 1 estimation of check-worthiness (the only task that has been present in all CheckThat! editions), Task 2 identification of subjectivity (a follow up of CheckThat! 2023 edition), Task 3 identification of persuasion (a follow up of SemEval 2023), Task 4 detection of hero, villain, and victim from memes (a follow up of CONSTRAINT 2022), Task 5 Rumor Verification using Evidence from Authorities (a first), and Task 6 robustness of credibility assessment with adversarial examples (a first). These tasks represent challenging classification and retrieval problems at the document and at the span level, including multilingual and multimodal settings.",
    isbn="978-3-031-56069-9",
}


@inproceedings{sadraeijavaeri2024superpos,
  title={SuperPos-Prompt: Enhancing Soft Prompt Tuning of Language Models with Superposition of Multi Token Embeddings},
  author={SadraeiJavaeri, MohammadAli and Asgari, Ehsaneddin and McHardy, Alice Carolyn and Rabiee, Hamid Reza},
  booktitle = "NeurIPS 2024 Workshop on Efficient Natural Language and Speech Processing",
  series = {NeurIPS~'24},
    month = "dec",
    year = "2024",
    address =  "Vancouver, Canada",
}


@inproceedings{zahraei2024turingq,
  title={TuringQ: Benchmarking AI Comprehension in Theory of Computation},
  author={Zahraei, Pardis Sadat and Asgari, Ehsaneddin},
  booktitle = "The 2024 Conference on Empirical Methods in Natural Language Processing",
  series={EMNLP~'24},
    month = "nov",
    year = "2024",
    publisher = "Association for Computational Linguistics",
}


@inproceedings{ghahroodi2024khayyam,
  title={Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language?},
  author={Ghahroodi, Omid and Nouri, Marzia and Sanian, Mohammad Vali and Sahebi, Alireza and Dastgheib, Doratossadat and Asgari, Ehsaneddin and Baghshah, Mahdieh Soleymani and Rohban, Mohammad Hossein},
  booktitle = "Proceedings of the Conference on Language Modeling (COLM) 2024",
  series = {COLM~'24},
  month = {October},
  year = "2024",
  publisher = "Conference on Language Modeling",
  address =  "Philadelphia, PA"
}

@inproceedings{mirzakhmedova-etal-2024-touche23,
    title = "The Touch{\'e}23-{V}alue{E}val Dataset for Identifying Human Values behind Arguments",
    author = "Mirzakhmedova, Nailia  and
      Kiesel, Johannes  and
      Alshomary, Milad  and
      Heinrich, Maximilian  and
      Handke, Nicolas  and
      Cai, Xiaoni  and
      Barriere, Valentin  and
      Dastgheib, Doratossadat  and
      Ghahroodi, Omid  and
      SadraeiJavaheri, MohammadAli  and
      Asgari, Ehsaneddin  and
      Kawaletz, Lea  and
      Wachsmuth, Henning  and
      Stein, Benno",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.1402",
    pages = "16121--16134",
}

@inproceedings{sadraeijavaheri-etal-2024-transformers,
    title = "Transformers for Bridging {P}ersian Dialects: Transliteration Model for Tajiki and {I}ranian Scripts",
    author = "SadraeiJavaheri, MohammadAli  and
      Asgari, Ehsaneddin  and
      Rabiee, Hamid Reza",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.lrec-main.1459",
    pages = "16770--16775",
}

@inproceedings{ghahroodi-asgari-2024-hierarchyeverywhere,
    title = "{H}ierarchy{E}verywhere at {S}em{E}val-2024 Task 4: Detection of Persuasion Techniques in Memes Using Hierarchical Text Classifier",
    author = "Ghahroodi, Omid  and
      Asgari, Ehsaneddin",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.semeval-1.247",
    doi = "10.18653/v1/2024.semeval-1.247",
    pages = "1727--1732",
}

@inproceedings{abootorabi-etal-2024-aima,
    title = "{AIMA} at {S}em{E}val-2024 Task 10: History-Based Emotion Recognition in {H}indi-{E}nglish Code-Mixed Conversations",
    author = "Abootorabi, Mohammad Mahdi  and
      Ghazizadeh, Nona  and
      Dalili, Seyed Arshan  and
      Ghahramani Kure, Alireza  and
      Dehghani, Mahshid  and
      Asgari, Ehsaneddin",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.semeval-1.244",
    doi = "10.18653/v1/2024.semeval-1.244",
    pages = "1704--1710",
}

@inproceedings{ghahramani-kure-etal-2024-aima,
    title = "{AIMA} at {S}em{E}val-2024 Task 3: Simple Yet Powerful Emotion Cause Pair Analysis",
    author = "Ghahramani Kure, Alireza  and
      Dehghani, Mahshid  and
      Abootorabi, Mohammad Mahdi  and
      Ghazizadeh, Nona  and
      Dalili, Seyed Arshan  and
      Asgari, Ehsaneddin",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.semeval-1.243",
    doi = "10.18653/v1/2024.semeval-1.243",
    pages = "1698--1703",
    abstract = "The SemEval-2024 Task 3 presents two subtasks focusing on emotion-cause pair extraction within conversational contexts. Subtask 1 revolves around the extraction of textual emotion-cause pairs, where causes are defined and annotated as textual spans within the conversation. Conversely, Subtask 2 extends the analysis to encompass multimodal cues, including language, audio, and vision, acknowledging instances where causes may not be exclusively represented in the textual data. Our proposed model for emotion-cause analysis is meticulously structured into three core segments: (i) embedding extraction, (ii) cause-pair extraction {\&} emotion classification, and (iii) cause extraction using QA after finding pairs. Leveraging state-of-the-art techniques and fine-tuning on task-specific datasets, our model effectively unravels the intricate web of conversational dynamics and extracts subtle cues signifying causality in emotional expressions. Our team, AIMA, demonstrated strong performance in the SemEval-2024 Task 3 competition. We ranked as the 10th in subtask 1 and the 6th in subtask 2 out of 23 teams.",
}

>>>>>>> upstream/master
@inproceedings{hasan-etal-2024-zero,
	address = {Torino, Italia},
	author = {Hasan, Md. Arid and Das, Shudipta and Anjum, Afiyat and Alam, Firoj and Anjum, Anika and Sarker, Avijit and Noori, Sheak Rashed Haider},
	booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
	date-modified = {2024-08-03 11:44:50 +0300},
	editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
	month = may,
	pages = {17808--17818},
	publisher = {ELRA and ICCL},
	title = {Zero- and Few-Shot Prompting with {LLM}s: A Comparative Study with Fine-tuned Models for {B}angla Sentiment Analysis},
	year = {2024},
	url = {https://aclanthology.org/2024.lrec-main.1549},
}

@inproceedings{alam-etal-2024-llms,
	address = {St. Julian{'}s, Malta},
	author = {Alam, Firoj and Chowdhury, Shammur Absar and Boughorbel, Sabri and Hasanain, Maram},
	booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Tutorial Abstracts},
	date-modified = {2024-08-03 11:44:50 +0300},
	editor = {Mesgar, Mohsen and Lo{\'a}iciga, Sharid},
	month = mar,
	pages = {27--33},
	publisher = {Association for Computational Linguistics},
	title = {{LLM}s for Low Resource Languages in Multilingual, Multimodal and Dialectal Settings},
	year = {2024},
	url = {https://aclanthology.org/2024.eacl-tutorials.5},
}

@inproceedings{abdelali-etal-2024-larabench,
	address = {St. Julian{'}s, Malta},
	author = {Abdelali, Ahmed and Mubarak, Hamdy and Chowdhury, Shammur and Hasanain, Maram and Mousi, Basel and Boughorbel, Sabri and Abdaljalil, Samir and El Kheir, Yassine and Izham, Daniel and Dalvi, Fahim and Hawasly, Majd and Nazar, Nizi and Elshahawy, Youssef and Ali, Ahmed and Durrani, Nadir and Milic-Frayling, Natasa and Alam, Firoj},
	booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
	date-modified = {2024-08-03 11:44:50 +0300},
	editor = {Graham, Yvette and Purver, Matthew},
	month = mar,
	pages = {487--520},
	publisher = {Association for Computational Linguistics},
	title = {{LA}ra{B}ench: Benchmarking {A}rabic {AI} with Large Language Models},
	year = {2024},
abstract = "Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific benchmarking against state-of-the-art (SOTA) models tailored to particular languages and tasks. LAraBench addresses this gap for Arabic Natural Language Processing (NLP) and Speech Processing tasks, including sequence tagging and content classification across different domains. We utilized models such as GPT-3.5-turbo, GPT-4, BLOOMZ, Jais-13b-chat, Whisper, and USM, employing zero and few-shot learning techniques to tackle 33 distinct tasks across 61 publicly available datasets. This involved 98 experimental setups, encompassing {\textasciitilde}296K data points, {\textasciitilde}46 hours of speech, and 30 sentences for Text-to-Speech (TTS). This effort resulted in 330+ sets of experiments. Our analysis focused on measuring the performance gap between SOTA models and LLMs. The overarching trend observed was that SOTA models generally outperformed LLMs in zero-shot learning, with a few exceptions. Notably, larger computational models with few-shot learning techniques managed to reduce these performance gaps. Our findings provide valuable insights into the applicability of LLMs for Arabic NLP and speech processing tasks.",
	url = {https://aclanthology.org/2024.eacl-long.30},
}

@inproceedings{dalvi-etal-2024-llmebench,
	address = {St. Julians, Malta},
	author = {Dalvi, Fahim and Hasanain, Maram and Boughorbel, Sabri and Mousi, Basel and Abdaljalil, Samir and Nazar, Nizi and Abdelali, Ahmed and Chowdhury, Shammur Absar and Mubarak, Hamdy and Ali, Ahmed and Hawasly, Majd and Durrani, Nadir and Alam, Firoj},
	booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations},
	date-modified = {2024-08-03 11:44:50 +0300},
	editor = {Aletras, Nikolaos and De Clercq, Orphee},
	month = mar,
	pages = {214--222},
	publisher = {Association for Computational Linguistics},
	title = {{LLM}e{B}ench: A Flexible Framework for Accelerating {LLM}s Benchmarking},
	year = {2024},
	abstract = "The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available, their customization capabilities for specific tasks and datasets are often complex for different users. In this study, we introduce the LLMeBench framework, which can be seamlessly customized to evaluate LLMs for any NLP task, regardless of language. The framework features generic dataset loaders, several model providers, and pre-implements most standard evaluation metrics. It supports in-context learning with zero- and few-shot settings. A specific dataset and task can be evaluated for a given LLM in less than 20 lines of code while allowing full flexibility to extend the framework for custom datasets, models, or tasks. The framework has been tested on 31 unique NLP tasks using 53 publicly available datasets within 90 experimental setups, involving approximately 296K data points. We open-sourced LLMeBench for the community (https://github.com/qcri/LLMeBench/) and a video demonstrating the framework is available online (https://youtu.be/9cC2m{\_}abk3A).",
	url = {https://aclanthology.org/2024.eacl-demo.23},
}

@inproceedings{dimitrov-etal-2024-semeval,
	address = {Mexico City, Mexico},
	author = {Dimitrov, Dimitar and Alam, Firoj and Hasanain, Maram and Hasnat, Abul and Silvestri, Fabrizio and Nakov, Preslav and Da San Martino, Giovanni},
	booktitle = {Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)},
	date-modified = {2024-08-03 11:44:50 +0300},
	editor = {Ojha, Atul Kr. and Do{\u{g}}ru{\"o}z, A. Seza and Tayyar Madabushi, Harish and Da San Martino, Giovanni and Rosenthal, Sara and Ros{\'a}, Aiala},
	month = jun,
	pages = {2009--2026},
	publisher = {Association for Computational Linguistics},
	title = {{S}em{E}val-2024 Task 4: Multilingual Detection of Persuasion Techniques in Memes},
	year = {2024},
	url = {https://aclanthology.org/2024.semeval-1.275},
	doi = {https://doi.org/10.18653/v1/2024.semeval-1.275},
}
@InProceedings{CheckThat:ECIR2024,
    author="Barr{\'o}n-Cede{\~{n}}o, Alberto
        and Alam, Firoj
        and Chakraborty, Tanmoy
        and Elsayed, Tamer
        and Nakov, Preslav
        and Przyby{\l}a, Piotr
        and Stru{\ss}, Julia Maria
        and Haouari, Fatima
        and Hasanain, Maram
        and Ruggeri, Federico
        and Song, Xingyi
        and Suwaileh, Reem",
    editor="Goharian, Nazli
        and Tonellotto, Nicola
        and He, Yulan
        and Lipani, Aldo
        and McDonald, Graham
        and Macdonald, Craig
        and Ounis, Iadh",
    title="The {CLEF}-2024 {C}heck{T}hat! {L}ab: Check-Worthiness, Subjectivity, Persuasion, Roles, Authorities, and Adversarial Robustness",
    booktitle="Advances in Information Retrieval",
    year="2024",
    publisher="Springer Nature Switzerland",
    NOaddress="Cham",
    pages="449--458",
    abstract="The first five editions of the CheckThat! lab focused on the main tasks of the information verification pipeline: check-worthiness, evidence retrieval and pairing, and verification. Since the 2023 edition, it has been focusing on new problems that can support the research and decision making during the verification process. In this new edition, we focus on new problems and ---for the first time--- we propose six tasks in fifteen languages (Arabic, Bulgarian, English, Dutch, French, Georgian, German, Greek, Italian, Polish, Portuguese, Russian, Slovene, Spanish, and code-mixed Hindi-English): Task 1 estimation of check-worthiness (the only task that has been present in all CheckThat! editions), Task 2 identification of subjectivity (a follow up of CheckThat! 2023 edition), Task 3 identification of persuasion (a follow up of SemEval 2023), Task 4 detection of hero, villain, and victim from memes (a follow up of CONSTRAINT 2022), Task 5 Rumor Verification using Evidence from Authorities (a first), and Task 6 robustness of credibility assessment with adversarial examples (a first). These tasks represent challenging classification and retrieval problems at the document and at the span level, including multilingual and multimodal settings.",
    isbn="978-3-031-56069-9",

}


@InProceedings{clef-checkthat:2024-lncs,
	author="Barr{\'o}n-Cede{\~{n}}o, Alberto
		and Alam, Firoj
        and Stru{\ss}, Julia Maria
        and Nakov, Preslav
        and Chakraborty, Tanmoy
        and Elsayed, Tamer
        and Przybyła, Piotr
		and Caselli, Tommaso
		and Da San Martino, Giovanni
		and Haouari, Fatima
        and Li, Chengkai
        and Piskorski, Jakub
		and Ruggeri, Federico
		and Song, Xingyi
        and Suwaileh, Reem",
	title="Overview of the {CLEF}-2024 {CheckThat! Lab}: Check-Worthiness, Subjectivity, Persuasion, Roles,
Authorities and Adversarial Robustness",
	editor="Goeuriot, Lorraine
        and Mulhem, Philippe
        and Quénot, Georges
        and Schwab, Didier
        and Soulier, Laure
        and Di Nunzio, Giorgio Maria
        and Galuščáková, Petra
        and García Seco de Herrera, Alba
        and Faggioli, Guglielmo
        and Ferro, Nicola",
	booktitle="Experimental IR Meets Multilinguality, Multimodality, and Interaction.
Proceedings of the Fifteenth International Conference of the CLEF Association (CLEF 2024)",
	year="2024",

}

@inproceedings{hasanain-etal-2023-araieval,
	address = {Singapore (Hybrid)},
	author = {Hasanain, Maram and Alam, Firoj and Mubarak, Hamdy and Abdaljalil, Samir and Zaghouani, Wajdi and Nakov, Preslav and Da San Martino, Giovanni and Freihat, Abed},
	booktitle = {Proceedings of ArabicNLP 2023},
	date-modified = {2024-08-03 11:44:50 +0300},
	editor = {Sawaf, Hassan and El-Beltagy, Samhaa and Zaghouani, Wajdi and Magdy, Walid and Abdelali, Ahmed and Tomeh, Nadi and Abu Farha, Ibrahim and Habash, Nizar and Khalifa, Salam and Keleg, Amr and Haddad, Hatem and Zitouni, Imed and Mrini, Khalil and Almatham, Rawan},
	month = dec,
	pages = {483--493},
	publisher = {Association for Computational Linguistics},
	title = {{A}r{AIE}val Shared Task: Persuasion Techniques and Disinformation Detection in {A}rabic Text},
	year = {2023},
	url = {https://aclanthology.org/2023.arabicnlp-1.44},
	bdsk-url-2 = {https://doi.org/10.18653/v1/2023.arabicnlp-1.44},
	bibtex_show={true}
	}

@article{sajjad-neuron-survey,
    title = "Neuron-level {I}nterpretation of {D}eep {NLP} {M}odels: {A} {S}urvey",
    author = "Sajjad, Hassan  and
      Durrani, Nadir  and
      Dalvi, Fahim",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "11",
    year = "2023",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    abstract = "The proliferation of deep neural networks in various domains has seen an increased need for interpretability of these models. Preliminary work done along this line and papers that surveyed such, are focused on high-level representation analysis. However, a recent branch of work has concentrated on interpretability at a more granular level of analyzing neurons within these models. In this paper, we survey the work done on neuron analysis including: i) methods to discover and understand neurons in a network, ii) evaluation methods, iii) major findings including cross architectural comparisons that neuron analysis has unraveled, iv) applications of neuron probing such as: controlling the model, domain adaptation etc., and v) a discussion on open issues and future research directions.",
}

@article{sajjad2023:csl,
  address = {London, UK, UK},
  author = {Sajjad, Hassan and Dalvi, Fahim and Durrani, Nadir and Nakov, Preslav},
  issn = {0885-2308},
  doi = {https://doi.org/10.1016/j.csl.2022.101429},
  url = {https://www.sciencedirect.com/science/article/pii/S0885230822000596},
  issue_date = {January 2023},
  journal = {Computer Speech and Language},
  number = {C},
  publisher = {Academic Press Ltd.},
  title = {On the Effect of Dropping Layers of Pre-trained Transformer Models},
  volume = {77},
  pages = {101429},
  year = {2023},
  area = {Transfer Learning}
}


@inproceedings{clef-checkthat:2023:task2,
	author = {Galassi, Andrea and Ruggeri, Federico and Barr\'{o}n-Cede\~{n}o, Alberto and Alam, Firoj and Caselli, Tommaso and Kutlu, Mucahid and Struss, {Julia Maria} and Antici, Francesco and Hasanain, Maram and K{\"o}hler, Juliane and Korre, Katerina and Leistra, Folkert and Muti, Arianna and Siegel, Melanie and Turkmen. {Mehmet Deniz} and Wiegand, Michael and Zaghouani, Wajdi},
	crossref = {clef2023-workingnotes},
	date-modified = {2024-08-03 12:29:30 +0300},
	title = {Overview of the {CLEF}-2023 {CheckThat}! Lab Task 2 on Subjectivity in News Articles},
	year = {2023},
}

@inproceedings{clef-checkthat:2023:task3,
	author = {Da San Martino, Giovanni and Alam, Firoj and Hasanain, Maram and Nandi, Rabindra Nath and Azizov, Dilshod and Nakov, Preslav},
	booktitle = {Working Notes of {CLEF} 2023 - Conference and Labs of the Evaluation Forum},
	crossref = {clef2023-workingnotes},
	date-modified = {2024-08-03 12:30:07 +0300},
	title = {Overview of the {CLEF}-2023 {CheckThat}! Lab Task 3 on Political Bias of News Articles and News Media},
	year = {2023},
}

@inproceedings{barron2023clef,
	author = {Barr{\'o}n-Cede{\~n}o, Alberto and Alam, Firoj and Caselli, Tommaso and Da San Martino, Giovanni and Elsayed, Tamer and Galassi, Andrea and Haouari, Fatima and Ruggeri, Federico and Stru{\ss}, Julia Maria and Nandi, Rabindra Nath and others},
	booktitle = {European Conference on Information Retrieval},
	organization = {Springer},
	pages = {506--517},
	title = {The clef-2023 checkthat! lab: Checkworthiness, subjectivity, political bias, factuality, and authority},
	year = {2023},
}

@inproceedings{nandi-etal-2023-pseudo,
	abstract = {One of the major challenges for developing automatic speech recognition (ASR) for low-resource languages is the limited access to labeled data with domain-specific variations. In this study, we propose a pseudo-labeling approach to develop a large-scale domain-agnostic ASR dataset. With the proposed methodology, we developed a 20k+ hours labeled Bangla speech dataset covering diverse topics, speaking styles, dialects, noisy environments, and conversational scenarios. We then exploited the developed corpus to design a conformer-based ASR system. We benchmarked the trained ASR with publicly available datasets and compared it with other available models. To investigate the efficacy, we designed and developed a human-annotated domain-agnostic test set composed of news, telephony, and conversational data among others. Our results demonstrate the efficacy of the model trained on psuedo-label data for the designed test-set along with publicly-available Bangla datasets. The experimental resources will be publicly available.https://github.com/hishab-nlp/Pseudo-Labeling-for-Domain-Agnostic-Bangla-ASR},
	address = {Singapore},
	author = {Nandi, Rabindra Nath and Menon, Mehadi and Muntasir, Tareq and Sarker, Sagor and Muhtaseem, Quazi Sarwar and Islam, Md. Tariqul and Chowdhury, Shammur and Alam, Firoj},
	booktitle = {Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)},
	date-modified = {2024-08-03 12:08:38 +0300},
	editor = {Alam, Firoj and Kar, Sudipta and Chowdhury, Shammur Absar and Sadeque, Farig and Amin, Ruhul},
	month = dec,
	pages = {152--162},
	publisher = {Association for Computational Linguistics},
	title = {Pseudo-Labeling for Domain-Agnostic {B}angla Automatic Speech Recognition},
	year = {2023},
	url = {https://aclanthology.org/2023.banglalp-1.16},
	doi = {https://doi.org/10.18653/v1/2023.banglalp-1.16},

}
@inproceedings{hasanain-etal-2024-large,
    title = "Large Language Models for Propaganda Span Annotation",
    author = "Hasanain, Maram  and
      Ahmad, Fatema  and
      Alam, Firoj",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.850/",
    doi = "10.18653/v1/2024.findings-emnlp.850",
    pages = "14522--14532"
}


@inproceedings{hasanain-etal-2024-gpt,
	address = {Torino, Italia},
	author = {Hasanain, Maram and Ahmad, Fatema and Alam, Firoj},
	booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
	date-modified = {2024-08-03 11:44:50 +0300},
	editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
	month = may,
	pages = {2724--2744},
	publisher = {ELRA and ICCL},
	title = {Can {GPT}-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles},
	year = {2024},
	url = {https://aclanthology.org/2024.lrec-main.244},
}


@inproceedings{hasanain-etal-2023-qcri,
    title = "{QCRI} at {S}em{E}val-2023 Task 3: News Genre, Framing and Persuasion Techniques Detection Using Multilingual Models",
    author = "Hasanain, Maram  and
      El-Shangiti, Ahmed  and
      Nandi, Rabindra Nath  and
      Nakov, Preslav  and
      Alam, Firoj",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Da San Martino, Giovanni  and
      Tayyar Madabushi, Harish  and
      Kumar, Ritesh  and
      Sartori, Elisa},
    booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.semeval-1.172",
    doi = "10.18653/v1/2023.semeval-1.172",
    pages = "1237--1244",
    abstract = "Misinformation spreading in mainstream and social media has been misleading users in different ways. Manual detection and verification efforts by journalists and fact-checkers can no longer cope with the great scale and quick spread of misleading information. This motivated research and industry efforts to develop systems for analyzing and verifying news spreading online. The SemEval-2023 Task 3 is an attempt to address several subtasks under this overarching problem, targeting writing techniques used in news articles to affect readers{'} opinions. The task addressed three subtasks with six languages, in addition to three {``}surprise{''} test languages, resulting in 27 different test setups. This paper describes our participating system to this task. Our team is one of the 6 teams that successfully submitted runs for all setups. The official results show that our system is ranked among the top 3 systems for 10 out of the 27 setups.",
}

@inproceedings{barron2023clef,
  title={The clef-2023 checkthat! lab: Checkworthiness, subjectivity, political bias, factuality, and authority},
  author={Barr{\'o}n-Cede{\~n}o, Alberto and Alam, Firoj and Caselli, Tommaso and Da San Martino, Giovanni and Elsayed, Tamer and Galassi, Andrea and Haouari, Fatima and Ruggeri, Federico and Stru{\ss}, Julia Maria and Nandi, Rabindra Nath and others},
  booktitle={European Conference on Information Retrieval},
  pages={506--517},
  year={2023},
  organization={Springer}
}

@inproceedings{nadir:emnlp:2022,
  title = "On the Transformation of Latent Space in Fine-Tuned NLP Models",
  author = "Nadir Durrani and Hassan Sajjad and Fahim Dalvi and Firoj Alam",
  booktitle = "The 2022 Conference on Empirical Methods in Natural Language Processing",
  series={EMNLP~'22},
    month = "dec",
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",

}
@inproceedings{abdelali-2021-arabic-transformers,
    title = "Post-hoc analysis of Arabic transformer models",
    author = "Abdelali, Ahmed  and
      Durrani, Nadir  and
      Dalvi, Fahim   and
      Sajjad, Hassan",
    booktitle = "Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
    month = "dec",
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    abstract = "Arabic is a Semitic language which is widely spoken with many dialects. Given the success of pre-trained language models, many transformer models trained on Arabic and its dialects have surfaced. While there have been an extrinsic evaluation of these models with respect to downstream NLP tasks, no work has been carried out to analyze and compare their internal representations. We probe how linguistic information is encoded in the transformer models, trained on different Arabic dialects. We perform a layer and neuron analysis on the models using morphological tagging tasks for different dialects of Arabic and a dialectal identification task. Our analysis enlightens interesting findings such as: i) word morphology is learned at the lower and middle layers, ii) while syntactic dependencies are predominantly captured at the higher layers, iii) despite a large overlap in their vocabulary, the MSA-based models fail to capture the nuances of Arabic dialects, iv) we found that neurons in embedding layers are polysemous in nature, while the neurons in middle layers are exclusive to specific properties.",
}



@inproceedings{alam-etal-2022-survey,
    title = "A Survey on Multimodal Disinformation Detection",
    author = "Alam, Firoj  and
      Cresci, Stefano  and
      Chakraborty, Tanmoy  and
      Silvestri, Fabrizio  and
      Dimitrov, Dimiter  and
      Martino, Giovanni Da San  and
      Shaar, Shaden  and
      Firooz, Hamed  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
    month = "oct",
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2022.coling-1.576",
    pages = "6625--6643",
    abstract = "Recent years have witnessed the proliferation of offensive content online such as fake news, propaganda, misinformation, and disinformation. While initially this was mostly about textual content, over time images and videos gained popularity, as they are much easier to consume, attract more attention, and spread further than text. As a result, researchers started leveraging different modalities and combinations thereof to tackle online multimodal offensive content. In this study, we offer a survey on the state-of-the-art on multimodal disinformation detection covering various combinations of modalities: text, images, speech, video, social media network structure, and temporal information. Moreover, while some studies focused on factuality, others investigated how harmful the content is. While these two components in the definition of disinformation {--} (i) factuality, and (ii) harmfulness {--}, are equally important, they are typically studied in isolation. Thus, we argue for the need to tackle disinformation detection by taking into account multiple modalities as well as both factuality and harmfulness, in the same framework. Finally, we discuss current challenges and future research directions.",
}

@inproceedings{sajjad-etal-2022-effect,
  title = {Effect of Post-processing on Contextualized Word Representations},
  author = {Sajjad, Hassan and Alam, Firoj and Dalvi, Fahim and Durrani, Nadir},
  booktitle = {Proceedings of the 29th International Conference on Computational Linguistics},
  month = "oct",
  year = {2022},
  address = {Gyeongju, Republic of Korea},
  publisher = {International Committee on Computational Linguistics},
  url = {https://aclanthology.org/2022.coling-1.277},
  pages = {3127--3142},
  area = {Representation Analysis}
}

@inproceedings{dalvi2022discovering,
  title={Discovering Latent Concepts Learned in {BERT}},
  author={Fahim Dalvi and Abdul Rafae Khan and Firoj Alam and Nadir Durrani and Jia Xu and Hassan Sajjad},
  booktitle={International Conference on Learning Representations},
  year={2022},
  url={https://openreview.net/forum?id=POTMtpYI1xH}
}

@inproceedings{sajjad:naacl:2022,
  title = "Analyzing Encoded Concepts in Transformer Language Models",
  author = "Hassan Sajjad and Nadir Durrani and Fahim Dalvi and Firoj Alam and Abdul Rafae Khan and Jia Xu",
  booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics",
  series={NAACL~'22},
  month = "Jul",
  year = "2022",
  address = "Seattle, Washington, USA",
  publisher = "Association for Computational Linguistics",
}

@inproceedings{alam-etal-2022-wanlp,
    title = "Overview of the WANLP 2022 Shared Task on Propaganda Detection in Arabic",
    author = "Firoj Alam and Hamdy Mubarak and Wajdi Zaghouani and Giovanni Da San Martino and Preslav Nakov",
    booktitle = "The Seventh Arabic Natural Language Processing Workshop (WANLP 2022) at EMNLP 2022",
    month = "dec",
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
}

@inproceedings{shaar-etal-2022-assisting,
    title = "Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document",
    author = "Shaden Shaar and Nikola Georgiev and Firoj Alam and Giovanni Da San Martino and Aisha Mohamed and Preslav Nakov",
    booktitle = "The 2022 Conference on Empirical Methods in Natural Language Processing",
    month = "dec",
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
}

@inproceedings{shaar-etal-2022-role,
    title = "The Role of Context in Detecting Previously Fact-Checked Claims",
    author = "Shaar, Shaden  and
      Alam, Firoj  and
      Da San Martino, Giovanni  and
      Nakov, Preslav",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
    month = "jul",
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-naacl.122",
    doi = "10.18653/v1/2022.findings-naacl.122",
    pages = "1619--1631",
    abstract = "Recent years have seen the proliferation of disinformation and fake news online. Traditional approaches to mitigate these issues is to use manual or automatic fact-checking. Recently, another approach has emerged: checking whether the input claim has previously been fact-checked, which can be done automatically, and thus fast, while also offering credibility and explainability, thanks to the human fact-checking and explanations in the associated fact-checking article. Here, we focus on claims made in a political debate and we study the impact of modeling the context of the claim: both on the source side, i.e., in the debate, as well as on the target side, i.e., in the fact-checking explanation document. We do this by modeling the local context, the global context, as well as by means of co-reference resolution, and multi-hop reasoning over the sentences of the document describing the fact-checked claim. The experimental results show that each of these represents a valuable information source, but that modeling the source-side context is most important, and can yield 10+ points of absolute improvement over a state-of-the-art model.",
}

@inproceedings{nakov2022fact,
  title={Fact-Checking, Fake News, Propaganda, Media Bias, and the {COVID-19} Infodemic},
  author={Nakov, Preslav and Da San Martino, Giovanni and Alam, Firoj},
  booktitle={Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining},
  pages={1632--1634},
  year={2022}
}

@inproceedings{mubarak2022arabgend,
 title = "{A}rab{G}end: Gender Analysis and Inference on {A}rabic {T}witter",
    author = "Mubarak, Hamdy  and
      Chowdhury, Shammur Absar  and
      Alam, Firoj",
    booktitle = "Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)",
    month = "oct",
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.wnut-1.14",
    pages = "124--135",
}



@InProceedings{mubarak-EtAl:2022:LREC,
  author    = {Mubarak, Hamdy  and  Hassan, Sabit  and  Chowdhury, Shammur Absar  and  Alam, Firoj},
  title     = {{ArCovidVac:} Analyzing Arabic Tweets About {COVID-19} Vaccination},
  booktitle      = {Proceedings of the Language Resources and Evaluation Conference},
  month          = {June},
  year           = {2022},
  address        = {Marseille, France},
  publisher      = {European Language Resources Association},
  pages     = {3220--3230},
  abstract  = {The emergence of the COVID-19 pandemic and the first global infodemic have changed our lives in many different ways. We relied on social media to get the latest information about COVID-19 pandemic and at the same time to disseminate information. The content in social media consisted not only health related advice, plans, and informative news from policymakers, but also contains conspiracies and rumors. It became important to identify such information as soon as they are posted to make an actionable decision (e.g., debunking rumors, or taking certain measures for traveling). To address this challenge, we develop and publicly release the first largest manually annotated Arabic tweet dataset, ArCovidVac, for COVID-19 vaccination campaign, covering many countries in the Arab region. The dataset is enriched with different layers of annotation, including, (i) Informativeness more vs. less importance of the tweets); (ii) fine-grained tweet content types (e.g., advice, rumors, restriction, authenticate news/information); and (iii) stance towards vaccination (pro-vaccination, neutral, anti-vaccination). Further, we performed in-depth analysis of the data, exploring the popularity of different vaccines, trending hashtags, topics, and presence of offensiveness in the tweets. We studied the data for individual types of tweets and temporal changes in stance towards vaccine. We benchmarked the ArCovidVac dataset using transformer architectures for informativeness, content types, and stance detection.},
  url       = {https://aclanthology.org/2022.lrec-1.344}
}


@inproceedings{nakov2022clef,
  title={The {CLEF-2022 CheckThat!} lab on fighting the {COVID-19} infodemic and fake news detection},
  author={Nakov, Preslav and Barr{\'o}n-Cede{\~n}o, Alberto and Da San Martino, Giovanni and Alam, Firoj and Stru{\ss}, Julia Maria and Mandl, Thomas and M{\'\i}guez, Rub{\'e}n and Caselli, Tommaso and Kutlu, Mucahid and Zaghouani, Wajdi and others},
  booktitle={European Conference on Information Retrieval},
  pages={416--428},
  year={2022},
  organization={Springer}
}

@article{ahmad2022global,
  title={Global User-Level Perception of {COVID-19} Contact Tracing Applications: Data-Driven Approach Using Natural Language Processing},
  author={Ahmad, Kashif and Alam, Firoj and Qadir, Junaid and Qolomany, Basheer and Khan, Imran and Khan, Talhat and Suleman, Muhammad and Said, Naina and Hassan, Syed Zohaib and Gul, Asma and others},
  journal={JMIR Formative Research},
  volume={6},
  number={5},
  pages={e36238},
  year={2022},
  publisher={JMIR Publications Inc., Toronto, Canada}
}

@article{nakov2022computational,
  Author = {Nakov, Preslav},
  Journal = {Creating a More Transparent Internet: The Perspective Web},
  Pages = {31},
  Publisher = {Cambridge University Press},
  Title = {Computational Linguistics for Subjectivity},
  Year = {2022}
  }

@inproceedings{sharma2022detecting,
  title     = {Detecting and Understanding Harmful Memes: A Survey},
  author    = {Sharma, Shivam and Alam, Firoj and Akhtar, Md. Shad and Dimitrov, Dimitar and Da San Martino, Giovanni and Firooz, Hamed and Halevy, Alon and Silvestri, Fabrizio and Nakov, Preslav and Chakraborty, Tanmoy},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence},
  series = {IJCAI~'22},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {5597--5606},
  year      = {2022},
  month     = {7},
  note      = {Survey Track},
  address = {Vienna, Austria},
  doi       = {10.24963/ijcai.2022/781},
  url       = {https://doi.org/10.24963/ijcai.2022/781},
  }

@inproceedings{nandi2022detecting,
  Author = {Nandi, Rabindra Nath and Alam, Firoj and Nakov, Preslav},
  Booktitle = {Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations},
  Pages = {43--54},
  Title = {Detecting the Role of an Entity in Harmful Memes: Techniques and their Limitations},
  Year = {2022}}

@inproceedings{nakov2022fact,
  Author = {Nakov, Preslav and Da San Martino, Giovanni and Alam, Firoj},
  Booktitle = {Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining},
  Pages = {1632--1634},
  Title = {Fact-Checking, Fake News, Propaganda, Media Bias, and the {COVID-19} Infodemic},
  Year = {2022}}

@article{huang2022faking,
  Author = {Huang, Kung-Hsiang and McKeown, Kathleen and Nakov, Preslav and Choi, Yejin and Ji, Heng},
  Journal = {arXiv preprint arXiv:2203.05386},
  Title = {Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation},
  Year = {2022}}

@inproceedings{muresan2022findings,
  Author = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  Booktitle = {{Findings of the Association for Computational Linguistics: ACL 2022}},
  Title = {Findings of the Association for Computational Linguistics: ACL 2022},
  Year = {2022}}

@inproceedings{sharma2022findings,
  Author = {Sharma, Shivam and Suresh, Tharun and Kulkarni, Atharva and Mathur, Himanshi and Nakov, Preslav and Akhtar, Md Shad and Chakraborty, Tanmoy},
  Booktitle = {Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations},
  Pages = {1--11},
  Title = {Findings of the {CONSTRAINT 2022} Shared Task on Detecting the Hero, the Villain, and the Victim in Memes},
  Year = {2022}}

@inproceedings{sharma2022md,
  Author = {Sharma, Shivam and Suresh, Tharun and Jitendra, Atharva and Mathur, Himanshi and Nakov, Preslav},
  Booktitle = {Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations-{CONSTRAINT}},
  Title = {Findings of the constraint 2022 shared task on detecting the hero, the villain, and the victim in memes},
  Year = {2022}}

@inproceedings{masud2022half,
  Author = {Masud, Sarah and Pinkesh, Pinkesh and Das, Amitava and Gupta, Manish and Nakov, Preslav and Chakraborty, Tanmoy},
  Booktitle = {Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining},
  Pages = {1629--1631},
  Title = {Half-Day Tutorial on Combating Online Hate Speech: The Role of Content, Networks, Psychology, User Behavior, etc.},
  Year = {2022}}

@inproceedings{muresan2022proceedings,
  Author = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
  Booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics},
  Title = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics},
  Year = {2022}
  }

@inproceedings{chakraborty2022proceedings,
  Author = {Chakraborty, Tanmoy and Akhtar, Md Shad and Shu, Kai and Bernard, H Russell and Liakata, Maria and Nakov, Preslav and Sharma, Shivam and Sharma, Chhavi and Kumar, Shivani and Atri, Yash Kumar and others},
  Booktitle = {Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations},
  Title = {Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations},
  Year = {2022}}

@article{nakov2022qcri,
  Author = {Nakov, Preslav and Alam, Firoj and Zhang, Yifan and Prakash, Animesh and Dalvi, Fahim},
  Journal = {arXiv preprint arXiv:2204.03506},
  Title = {{QCRI's} {COVID-19} Disinformation Detector: A System to Fight the {COVID-19} Infodemic in Social Media},
  Year = {2022}}



@inproceedings{nandi2022teamx,
  Author = {Nandi, Rabindra Nath and Alam, Firoj and Nakov, Preslav},
  Booktitle = {Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages},
  Pages = {79--85},
  Title = {TeamX@ DravidianLangTech-ACL2022: A Comparative Analysis for Troll-Based Meme Classification},
  Year = {2022}}

@article{alam2021medic,
  title={MEDIC: a multi-task learning dataset for disaster image classification},
  author={Alam, Firoj and Alam, Tanvirul and Hasan, Md and Hasnat, Abul and Imran, Muhammad and Ofli, Ferda and others},
  journal={arXiv preprint arXiv:2108.12828},
  year={2021}
}

@article{alsmadi2021adversarial,
  title={Adversarial attacks and defenses for social network text processing applications: Techniques, challenges and future research directions},
  author={Alsmadi, Izzat and Ahmad, Kashif and Nazzal, Mahmoud and Alam, Firoj and Al-Fuqaha, Ala and Khreishah, Abdallah and Algosaibi, Abdulelah},
  journal={arXiv preprint arXiv:2110.13980},
  year={2021}
}

@article{nakov202111,
  Author = {Nakov, Preslav and Tiedemann, J{\"o}rg},
  Journal = {Similar Languages, Varieties, and Dialects: A Computational Perspective},
  Pages = {219},
  Publisher = {Cambridge University Press},
  Title = {11 Machine Translation between Similar Languages},
  Year = {2021}}

@inproceedings{da2021survey,
  Author = {Da San Martino, Giovanni and Cresci, Stefano and Barr{\'o}n-Cede{\~n}o, Alberto and Yu, Seunghak and Di Pietro, Roberto and Nakov, Preslav},
  Booktitle = {Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence},
  Pages = {4826--4832},
  Title = {A survey on computational propaganda detection},
  Year = {2021}}

@article{alam2021survey,
  Author = {Alam, Firoj and Cresci, Stefano and Chakraborty, Tanmoy and Silvestri, Fabrizio and Dimitrov, Dimiter and Martino, Giovanni Da San and Shaar, Shaden and Firooz, Hamed and Nakov, Preslav},
  Journal = {arXiv preprint arXiv:2103.12541},
  Title = {A survey on multimodal disinformation detection},
  Year = {2021}}

@article{nakov2021survey,
  Author = {Nakov, Preslav and Sencar, Husrev Taha and An, Jisun and Kwak, Haewoon},
  Journal = {arXiv preprint arXiv:2103.12506},
  Title = {A survey on predicting the factuality and the bias of news media},
  Year = {2021}}

@article{hardalov2021survey,
  Author = {Hardalov, Momchil and Arora, Arnav and Nakov, Preslav and Augenstein, Isabelle},
  Journal = {arXiv preprint arXiv:2103.00242},
  Title = {A survey on stance detection for mis-and disinformation identification},
  Year = {2021}}


@inproceedings{alhindi2021arastance,
  Author = {Alhindi, Tariq and Alabdulkarim, Amal and Alshehri, Ali and Abdul-Mageed, Muhammad and Nakov, Preslav},
  Booktitle = {Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda},
  Pages = {57--65},
  Title = {AraStance: A Multi-Country and Multi-Domain Dataset of Arabic Stance Detection for Fact Checking},
  Year = {2021}}



@inproceedings{survey:2021:ai:fact-checkers,
  Author = {Preslav Nakov and David Corney and Maram Hasanain and Firoj Alam and Tamer Elsayed and Alberto Barr{\'{o}}n{-}Cede{\~{n}}o and Paolo Papotti and Shaden Shaar and Giovanni {Da San Martino}},
  Booktitle = {Proceedings of the 30th International Joint Conference on Artificial Intelligence},
  Pages = {4551--4558},
  Series = {IJCAI~'21},
  Title = {Automated Fact-Checking for Assisting Human Fact-Checkers},
  Year = {2021}}

@article{chernyavskiy2021batch,
  Author = {Chernyavskiy, Anton and Ilvovsky, Dmitry and Kalinin, Pavel and Nakov, Preslav},
  Journal = {arXiv preprint arXiv:2110.15725},
  Title = {Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring Tasks},
  Year = {2021}}

@article{skuczynska2021beasku,
  Author = {Skuczy{\'n}ska, Beata and Shaar, Shaden and Spenader, Jennifer and Nakov, Preslav},
  Title = {BeaSku at CheckThat! 2021: fine-tuning sentence BERT with triplet loss and limited data},
  Year = {2021}}

@article{ganesh2021compressing,
  Author = {Ganesh, Prakhar and Chen, Yao and Lou, Xin and Khan, Mohammad Ali and Yang, Yin and Sajjad, Hassan and Nakov, Preslav and Chen, Deming and Winslett, Marianne},
  Journal = {Transactions of the Association for Computational Linguistics},
  Pages = {1061--1080},
  Title = {Compressing Large-Scale Transformer-Based Models: A Case Study on BERT},
  Volume = {9},
  Year = {2021}}

@article{nakov2021detecting,
  Author = {Nakov, Preslav and Nayak, Vibha and Dent, Kyle and Bhatawdekar, Ameya and Sarwar, Sheikh Muhammad and Hardalov, Momchil and Dinkov, Yoan and Zlatkova, Dimitrina and Bouchard, Guillaume and Augenstein, Isabelle},
  Journal = {arXiv preprint arXiv:2103.00153},
  Title = {Detecting abusive language on online platforms: A critical analysis},
  Year = {2021}}

@inproceedings{pramanick2021detecting,
  Author = {Pramanick, Shraman and Dimitrov, Dimitar and Mukherjee, Rituparna and Sharma, Shivam and Akhtar, Md Shad and Nakov, Preslav and Chakraborty, Tanmoy},
  Booktitle = {Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021},
  Pages = {2783--2796},
  Title = {Detecting Harmful Memes and Their Targets},
  Year = {2021}}

@inproceedings{dimitrov2021detecting,
  Author = {Dimitrov, Dimitar and Ali, Bishr Bin and Shaar, Shaden and Alam, Firoj and Silvestri, Fabrizio and Firooz, Hamed and Nakov, Preslav and Da San Martino, Giovanni},
  Booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  Pages = {6603--6617},
  Title = {Detecting Propaganda Techniques in Memes},
  Year = {2021}}

@article{nguyen2021dialect,
  Author = {Nguyen, Dong and Zampieri, Marcos and Nakov, Preslav and others},
  Publisher = {Cambridge University Press},
  Title = {Dialect Variation on Social Media},
  Year = {2021}}

@inproceedings{mihaylova2021dips,
  Author = {Mihaylova, Simona and Borisova, Iva and Chemishanov, Dzhovani and Hadzhitsanev, Preslav and Hardalov, Momchil and Nakov, Preslav},
  Title = {DIPS at CheckThat! 2021: Verified Claim Retrieval.},
  Year = {2021}}


@incollection{nastase2021extracting,
  Author = {Nastase, Vivi and Szpakowicz, Stan and Nakov, Preslav and S{\'e}agdha, Diarmuid {\'O}},
  Booktitle = {Semantic Relations Between Nominals, Second Edition},
  Pages = {75--106},
  Publisher = {Springer},
  Title = {Extracting Semantic Relations with Little or No Supervision},
  Year = {2021}}

@inproceedings{nakov2021fake,
  Author = {Nakov, Preslav and Da San Martino, Giovanni},
  Booktitle = {Proceedings of the 30th ACM International Conference on Information \& Knowledge Management},
  Pages = {4862--4865},
  Title = {Fake News, Disinformation, Propaganda, and Media Bias},
  Year = {2021}}

@inproceedings{nakov2021fake2,
  Author = {Nakov, Preslav and Da San Martino, Giovanni},
  Booktitle = {Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \& Data Mining},
  Pages = {4054--4055},
  Title = {Fake News, Disinformation, Propaganda, Media Bias, and Flattening the Curve of the COVID-19 Infodemic},
  Year = {2021}}

@inproceedings{alam2021fightingicwsm,
  Author = {Alam, Firoj and Dalvi, Fahim and Shaar, Shaden and Durrani, Nadir and Mubarak, Hamdy and Nikolov, Alex and Da San Martino, Giovanni and Abdelali, Ahmed and Sajjad, Hassan and Darwish, Kareem and others},
  Booktitle = {ICWSM},
  Pages = {913--922},
  Title = {Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms.},
  Year = {2021}}

@inproceedings{alam2021fighting,
  Author = {Alam, Firoj and Shaar, Shaden and Dalvi, Fahim and Sajjad, Hassan and Nikolov, Alex and Mubarak, Hamdy and Da San Martino, Giovanni and Abdelali, Ahmed and Durrani, Nadir and Darwish, Kareem and others},
  Booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2021},
  Pages = {611--649},
  Title = {Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society},
  Year = {2021}}

@inproceedings{shaar2021findings,
  Author = {Shaar, Shaden and Alam, Firoj and Da San Martino, Giovanni and Nikolov, Alex and Zaghouani, Wajdi and Nakov, Preslav and Feldman, Anna},
  Booktitle = {Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda},
  Pages = {82--92},
  Title = {Findings of the {NLP4IF-2021} Shared Tasks on Fighting the COVID-19 Infodemic and Censorship Detection},
  Year = {2021}}

@inproceedings{vachev2021generating,
  Author = {Vachev, Kristiyan and Hardalov, Momchil and Karadzhov, Georgi and Georgiev, Georgi and Koychev, Ivan and Nakov, Preslav},
  Booktitle = {Proceedings of the Student Research Workshop Associated with {RANLP}},
  Pages = {203--209},
  Title = {Generating Answer Candidates for Quizzes and Answer-Aware Question Generators},
  Year = {2021}}


@inproceedings{yu2021interpretable,
  Author = {Yu, Seunghak and Da San Martino, Giovanni and Mohtarami, Mitra and Glass, James and Nakov, Preslav},
  Booktitle = {Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)},
  Pages = {1597--1605},
  Title = {Interpretable Propaganda Detection in News Articles},
  Year = {2021}}

@article{nakov2021jisun,
  Author = {Nakov, Preslav and Sencar, Husrev Taha},
  Journal = {A survey on predicting the factuality and the bias of news media. arXiv/2103.12506},
  Title = {Jisun An, and Haewoon Kwak. 2021 c},
  Year = {2021}}

@inproceedings{pramanick2021momenta,
  Author = {Pramanick, Shraman and Sharma, Shivam and Dimitrov, Dimitar and Akhtar, Md Shad and Nakov, Preslav and Chakraborty, Tanmoy},
  Booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2021},
  Pages = {4439--4455},
  Title = {MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets},
  Year = {2021}}



@inproceedings{nakov2021overview,
  Author = {Nakov, Preslav and Da San Martino, Giovanni and Elsayed, Tamer and Barr{\'o}n-Cede{\~n}o, Alberto and M{\'\i}guez, Rub{\'e}n and Shaar, Shaden and Alam, Firoj and Haouari, Fatima and Hasanain, Maram and Mansour, Watheq and others},
  Booktitle = {International Conference of the Cross-Language Evaluation Forum for European Languages},
  Organization = {Springer},
  Pages = {264--291},
  Title = {Overview of the CLEF--2021 CheckThat! lab on detecting check-worthy claims, previously fact-checked claims, and fake news},
  Year = {2021}}

@article{shaar2021alberto,
  Author = {Shaar, Shaden and Hasanain, Maram and Hamdan, Bayan and Ali, Zien Sheikh and Haouari, Fatima and Nikolov, Alex and Kutlu, Mucahid and Kartal, Yavuz Selim and Alam, Firoj and Da San Martino, Giovanni Alberto Barr{\'o} n-Cede no, Rub{\'e}n M{\'\i}guez, Javier Beltr{\'a}n, Tamer Elsayed, and Preslav Nakov},
  Journal = {Working Notes of CLEF},
  Title = {Overview of the CLEF-2021 CheckThat! Lab Task 1 on Check-Worthiness Estimation in Tweets and Political Debates},
  Year = {2021}}

@inproceedings{bozhanova2021predicting,
  Author = {Bozhanova, Krasimira and Dinkov, Yoan and Koychev, Ivan and Castaldo, Maria and Venturini, Tommaso and Nakov, Preslav},
  Booktitle = {Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)},
  Pages = {182--189},
  Title = {Predicting the Factuality of Reporting of News Media Using Observations about User Attention in Their YouTube Channels},
  Year = {2021}}



@inproceedings{babych2021proceedings,
  Author = {Babych, Bogdan and Kanishcheva, Olga and Nakov, Preslav and Piskorski, Jakub and Pivovarova, Lidia and Starko, Vasyl and Steinberger, Josef and Yangarber, Roman and Marci{\'n}czuk, Micha{\l} and Pollak, Senja and others},
  Booktitle = {Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing},
  Title = {Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing},
  Year = {2021}}

@inproceedings{feldman2021proceedings,
  Author = {Feldman, Anna and Da San Martino, Giovanni and Leberknight, Chris and Nakov, Preslav},
  Booktitle = {Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda},
  Title = {Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda},
  Year = {2021}}

@incollection{nastase2021relations,
  Author = {Nastase, Vivi and Szpakowicz, Stan and Nakov, Preslav and S{\'e}agdha, Diarmuid {\'O}},
  Booktitle = {Semantic Relations Between Nominals, Second Edition},
  Pages = {11--30},
  Publisher = {Springer},
  Title = {Relations Between Nominals, Relations Between Concepts},
  Year = {2021}}

@incollection{nastase2021semantic,
  Author = {Nastase, Vivi and Szpakowicz, Stan and Nakov, Preslav and S{\'e}agdha, Diarmuid {\'O}},
  Booktitle = {Semantic Relations Between Nominals, Second Edition},
  Pages = {107--164},
  Publisher = {Springer},
  Title = {Semantic Relations and Deep Learning},
  Year = {2021}}

@article{nastase2021semantic2,
  Author = {Nastase, Vivi and Szpakowicz, Stan and Nakov, Preslav and S{\'e}agdha, Diarmuid {\'O}},
  Journal = {Synthesis lectures on human language technologies},
  Number = {1},
  Pages = {1--234},
  Publisher = {Morgan \& Claypool Publishers},
  Title = {Semantic relations between nominals},
  Volume = {14},
  Year = {2021}}

@inproceedings{dimitrov2021semeval,
  Author = {Dimitrov, Dimitar and Ali, Bishr Bin and Shaar, Shaden and Alam, Firoj and Silvestri, Fabrizio and Firooz, Hamed and Nakov, Preslav and Da San Martino, Giovanni},
  Booktitle = {Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)},
  Pages = {70--98},
  Title = {SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images},
  Year = {2021}}

@book{zampieri2021similar,
  Author = {Zampieri, Marcos and Nakov, Preslav},
  Publisher = {Cambridge University Press},
  Title = {Similar Languages, Varieties, and Dialects: A Computational Perspective},
  Year = {2021}}

@inproceedings{piskorski2021slav,
  Author = {Piskorski, Jakub and Babych, Bogdan and Kancheva, Zara and Kanishcheva, Olga and Lebedeva, Maria and Marci{\'n}czuk, Micha{\l} and Nakov, Preslav and Osenova, Petya and Pivovarova, Lidia and Pollak, Senja and others},
  Booktitle = {Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing},
  Pages = {122--133},
  Title = {Slav-NER: the 3rd Cross-lingual Challenge on Recognition, Normalization, Classification, and Linking of Named Entities across Slavic Languages},
  Year = {2021}}

@inproceedings{rosenthal2021solid,
  Author = {Rosenthal, Sara and Atanasova, Pepa and Karadzhov, Georgi and Zampieri, Marcos and Nakov, Preslav},
  Booktitle = {Findings of the Association for Computational Linguistics: {ACL-IJCNLP} 2021},
  Pages = {915--928},
  Title = {SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification},
  Year = {2021}}

@inproceedings{nakov2021clef,
  Author = {Nakov, Preslav and Da San Martino, Giovanni and Elsayed, Tamer and Barr{\'o}n-Cedeno, Alberto and M{\'\i}guez, Rub{\'e}n and Shaar, Shaden and Alam, Firoj and Haouari, Fatima and Hasanain, Maram and Babulkov, Nikolay and others},
  Booktitle = {European Conference on Information Retrieval},
  Organization = {Springer},
  Pages = {639--649},
  Title = {The CLEF-2021 CheckThat! lab on detecting check-worthy claims, previously fact-checked claims, and fake news},
  Year = {2021}}

@article{hristakieva2021spread,
  Author = {Hristakieva, Kristina and Cresci, Stefano and Martino, Giovanni Da San and Conti, Mauro and Nakov, Preslav},
  Journal = {arXiv preprint arXiv:2109.13046},
  Title = {The spread of propaganda by coordinated communities on social media},
  Year = {2021}}

@inproceedings{chernyavskiy2021transformers,
  Author = {Chernyavskiy, Anton and Ilvovsky, Dmitry and Nakov, Preslav},
  Booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases},
  Organization = {Springer},
  Pages = {677--693},
  Title = {Transformers:``The End of History'' for Natural Language Processing?},
  Year = {2021}}



@inproceedings{dangovski2021we,
  Author = {Dangovski, Rumen and Shen, Michelle and Byrd, Dawson and Jing, Li and Tsvetkova, Desislava and Nakov, Preslav and Solja{\v{c}}i{\'c}, Marin},
  Booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  Number = {14},
  Pages = {12728--12737},
  Title = {We Can Explain Your Research in Layman's Terms: Towards Automating Science Journalism at Scale},
  Volume = {35},
  Year = {2021}}

@inproceedings{chernyavskiy2021whatthewikifact,
  Author = {Chernyavskiy, Anton and Ilvovsky, Dmitry and Nakov, Preslav},
  Booktitle = {Proceedings of the 30th ACM International Conference on Information \& Knowledge Management},
  Pages = {4690--4695},
  Title = {WhatTheWikiFact: Fact-Checking Claims Against Wikipedia},
  Year = {2021}}


@article{darwish2021arabic,
  title={Arabic diacritic recovery using a feature-rich bilstm model},
  author={Darwish, Kareem and Abdelali, Ahmed and Mubarak, Hamdy and Eldesouki, Mohamed},
  journal={Transactions on Asian and Low-Resource Language Information Processing},
  volume={20},
  number={2},
  pages={1--18},
  year={2021},
  publisher={ACM New York, NY}
}


@article{darwish2021panoramic,
  title={A panoramic survey of natural language processing in the Arab world},
  author={Darwish, Kareem and Habash, Nizar and Abbas, Mourad and Al-Khalifa, Hend and Al-Natsheh, Huseein T and Bouamor, Houda and Bouzoubaa, Karim and Cavalli-Sforza, Violetta and El-Beltagy, Samhaa R and El-Hajj, Wassim and others},
  journal={Communications of the ACM},
  volume={64},
  number={4},
  pages={72--81},
  year={2021},
  publisher={ACM New York, NY, USA}
}



@inproceedings{mubarak2020arabic,
  title={Arabic Curriculum Analysis},
  author={Mubarak, Hamdy and Amer, Shimaa and Abdelali, Ahmed and Darwish, Kareem},
  booktitle={Proceedings of the 28th International Conference on Computational Linguistics: System Demonstrations},
  pages={80--86},
  year={2020}
}



@inproceedings{chowdhury2020improving,
  title={Improving Arabic text categorization using transformer training diversification},
  author={Chowdhury, Shammur Absar and Abdelali, Ahmed and Darwish, Kareem and Soon-Gyo, Jung and Salminen, Joni and Jansen, Bernard J},
  booktitle={Proceedings of the Fifth Arabic Natural Language Processing Workshop},
  pages={226--236},
  year={2020}
}



@article{harrag2021bert,
  title={Bert transformer model for detecting Arabic GPT2 auto-generated tweets},
  author={Harrag, Fouzi and Debbah, Maria and Darwish, Kareem and Abdelali, Ahmed},
  journal={arXiv preprint arXiv:2101.09345},
  year={2021}
}



@article{abdelali2021pre,
  title={Pre-Training BERT on Arabic Tweets: Practical Considerations},
  author={Abdelali, Ahmed and Hassan, Sabit and Mubarak, Hamdy and Darwish, Kareem and Samih, Younes},
  journal={arXiv preprint arXiv:2102.10684},
  year={2021}
}



@inproceedings{samih2021few,
  title={A Few Topical Tweets are Enough for Effective User Stance Detection},
  author={Samih, Younes and Darwish, Kareem},
  booktitle={Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume},
  pages={2637--2646},
  year={2021}
}



@inproceedings{abdelali2021qadi,
  title={QADI: Arabic Dialect Identification in the Wild},
  author={Abdelali, Ahmed and Mubarak, Hamdy and Samih, Younes and Hassan, Sabit and Darwish, Kareem},
  booktitle={Proceedings of the Sixth Arabic Natural Language Processing Workshop},
  pages={1--10},
  year={2021}
}

@inproceedings{alam2021icwsmfighting,
	title={Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms},
	author={Firoj Alam and Fahim Dalvi and Shaden Shaar and Nadir Durrani and Hamdy Mubarak and Alex Nikolov and Giovanni Da San Martino and Ahmed Abdelali and Hassan Sajjad and Kareem Darwish and Preslav Nakov},
	year={2021},
	booktitle={ICWSM},
}

@inproceedings{alam2021humaid,
	title={{HumAID}: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks},
	author={F. {Alam} and U. {Qazi} and M. {Imran} and F. {Ofli}},
	booktitle={ICWSM},
	year={2021}
}

@inproceedings{alam2020standardizing,
	title={CrisisBench: Benchmarking Crisis-related Social Media Datasets for Humanitarian Information Processing},
	author={Alam, Firoj and Sajjad, Hassan and Imran, Muhammad and Ofli, Ferda},
	booktitle={ICWSM},
	year={2021}
}

@INPROCEEDINGS{Alam9381294,
	author={Firoj  Alam and Ferda Ofli and Muhammad Imran and Tanviril  Alam and Umair Qazi},
	booktitle={ASONAM},
	title={Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Response},
	year={2020},
	pages={151-158},
	doi={10.1109/ASONAM49781.2020.9381294}
}

@inproceedings{alam-etal-2020-punctuation,
	title = "Punctuation Restoration using Transformer Models for High-and Low-Resource Languages",
	author = "Alam, Tanvirul  and
	Khan, Akib  and
	Alam, Firoj",
	booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
	month = "nov",
	year = "2020",
	address = "Online",
	publisher = "Association for Computational Linguistics",
	url = "https://www.aclweb.org/anthology/2020.wnut-1.18",
	doi = "10.18653/v1/2020.wnut-1.18",
	pages = "132--142",
}

@inproceedings{hassan-etal-2021-asad,
	title = "{ASAD}: {A}rabic Social media Analytics and un{D}erstanding",
	author = "Hassan, Sabit  and
	Mubarak, Hamdy  and
	Abdelali, Ahmed  and
	Darwish, Kareem",
	booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
	month = "apr",
	year = "2021",
	address = "Online",
	publisher = "Association for Computational Linguistics",
	url = "https://www.aclweb.org/anthology/2021.eacl-demos.14",
	pages = "113--118",
	abstract = "This system demonstration paper describes ASAD: Arabic Social media Analysis and unDerstanding, a suite of seven individual modules that allows users to determine dialects, sentiment, news category, offensiveness, hate speech, adult content, and spam in Arabic tweets. The suite is made available through a web API and a web interface where users can enter text or upload files.",
}

@inproceedings{INTERSPEECH2020:ADIAnalysis,
  title={What does an End-to-End Dialect Identification Model Learn about Non-dialectal Information?},
  author={Shammur Absar Chowdhury and Ahmed Ali and Suwon Shon and James Glass},
  booktitle={Proceedings of the 21st Annual Conference of the International Speech Communication Association (INTERSPEECH'20)},
  series = {INTERSPEECH~'20},
  address = {Shanghai, China},
  year={2020},
}

@inproceedings{INTERSPEECH2020:DACS,
  title={Effects of Dialectal Code-Switching on Speech Modules: A Study using Egyptian Arabic Broadcast Speech},
  author={Shammur Absar Chowdhury and Younes Samih and Mohamed Eldesouki and Ahmed Ali},
  booktitle={Proceedings of the 21st Annual Conference of the International Speech Communication Association (INTERSPEECH'20)},
  series = {INTERSPEECH~'20},
  address = {Shanghai, China},
  year={2020},
}


@misc{mubarak2020arabic,
    title={Arabic Offensive Language on Twitter: Analysis and Experiments},
    author={Hamdy Mubarak and Ammar Rashed and Kareem Darwish and Younes Samih and Ahmed Abdelali},
    year={2020},
    eprint={2004.02192},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

@inproceedings{abbes2018towards,
  title="Towards OpenDomain CrossLanguage Question Answering",
  author="Abbes, Ines and
	Barr{\'o}n-Cede{\~n}o, Alberto and
	Jemni, Mohamed",
  booktitle="Qatar Foundation Annual Research Conference Proceedings",
  volume="2018",
  number="3",
  pages="ICTPD881",
  year="2018",
  organization="HBKU Press Qatar"
}

@InProceedings{clef2018checkthat:task1,
    author    = "Atanasova, Pepa and
	    M\`{a}rquez, Llu\'{i}s  and
	    Barr\'{o}n-Cede\~{n}o, Alberto and
	    Elsayed, Tamer and
	    Suwaileh, Reem and
	    Zaghouani, Wajdi and
	    Kyuchukov, Spas and
	    Da San Martino, Giovanni and
	    Nakov, Preslav",
    title     = "Overview of the {CLEF-2018 CheckThat}! Lab on Automatic Identification and Verification of Political Claims, Task 1: Check-Worthiness",
    booktitle = "CLEF 2018 Working Notes. Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum (CLEF'18)",
    series    = "{CEUR} Workshop Proceedings",
    publisher = "CEUR-WS.org",
    editor    = "Cappellato, Linda and Ferro, Nicola and Nie, Jian-Yun and Soulier, Laure",
    address   = "Avignon, France",
    month     = "September",
    url       = "http://ceur-ws.org/Vol-2125/invited_paper_13.pdf",
    year      = "2018",
}


@InProceedings{Factuality:ordinal:2019,
  author =  "Baly, Ramy and
            Karadzhov, Georgi and
            Saleh, Abdelrhman and
            Glass, James and
            Nakov, Preslav",
  title =   "Multi-Task Ordinal Regression for Jointly Predicting the Trustworthiness and the Leading Political Ideology News Media",
  booktitle = {Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL'19)},
  series    = {NAACL-HLT~'19},
  year =  "2019",
  pages = "2109--2116",
  publisher =   "Association for Computational Linguistics",
  address =  "Minneapolis, MN, USA",
  url = "https://www.aclweb.org/anthology/N19-1216"
}

@InProceedings{baly-EtAl:2018:N18-2,
  author    = "Baly, Ramy  and
	  Mohtarami, Mitra  and
	  Glass, James  and
	  M\`{a}rquez, Llu\'{i}s  and
	  Moschitti, Alessandro  and
	  Nakov, Preslav",
  title     = "Integrating Stance Detection and Fact Checking in a Unified Corpus",
  booktitle = "Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT'18)",
  series    = "NAACL-HLT'18",
  month     = "June",
  year      = "2018",
  address   = "New Orleans, LA",
  publisher = "Association for Computational Linguistics",
  pages     = "21--27",
  url       = "http://www.aclweb.org/anthology/N18-2004"
}

@article{barron2016convkn,
  title="ConvKN at SemEval-2016 Task 3: Answer and question selection for question answering on Arabic and English fora",
  author="Barr{\'o}n-Cede{\~n}o, Alberto and
	  Bonadiman, Daniele and
	  Da San Martino, Giovanni and
	  Joty, Shafiq and
	  Moschitti, Alessandro and
	  Al Obaidli, Fahad A and
	  Romeo, Salvatore and
	  Tymoshenko, Kateryna and
	  Uva, Antonio",
  journal="Proceedings of SemEval-2016",
  pages="896--903",
  year="2016",
  publisher="Association for Computational Linguistics",
  url	= "https://aclweb.org/anthology/papers/S/S16/S16-1138/"

}

@inproceedings{barron2017use,
  author="Barr{\'o}n-Cede{\~n}o, Alberto and
	  Da San Martino, Giovanni and
	  Filice, Simone and
	  Moschitti, Alessandro",
  title="On the Use of an Intermediate Class in Boolean Crowdsourced Relevance Annotations for Learning to Rank Comments",
  booktitle="Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval",
  pages="1209--1212",
  year="2017",
  organization="ACM"
}

@article{Barron:19,
    author    = "Barr\'{o}n-Cede\~no, Alberto and
                Da San Martino, Giovanni and
                Jaradat, Israa and
                Nakov, Preslav",
    title     = "Proppy: Organizing News Coverage on the Basis of Their Propagandistic Content",
    journal   = "Information Processing and Management",
    year      = "2019"
}

@inproceedings{barron2016selecting,
  author="Barr{\'o}n-Cede\~no, Alberto and
	Da San Martino, Giovanni and
	Romeo, Salvatore and
	Moschitti, Alessandro",
  title="Selecting sentences versus selecting tree constituents for automatic question ranking",
  booktitle="Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
  pages="2515--2525",
  year="2016",
  url = "https://aclweb.org/anthology/papers/C/C16/C16-1237/"
}


@inproceedings{Barron:18,
 author = "Barr\'{o}n-Cede\~no, Alberto and
          Da San Martino, Giovanni and
          Zhang, Yifan and
          Ali, Ahmed and
          Dalvi, Fahim",
 title = "{Qlusty: Quick and Dirty Generation of Event Videos from Written Media Coverage}",
 booktitle = "Proceedings of the Second International Workshop on Recent Trends in News Information Retrieval",
 pages = "27--32",
 url = "http://ceur-ws.org/Vol-2079/paper7.pdf",
 address = "Grenoble, France",
 year = 2018
}

@InProceedings{clef2018checkthat:task2,
    author  = "Barr\'{o}n-Cede\~o, Alberto and
	    Elsayed, Tamer and
	    Suwaileh, Reem and
	    M\`{a}rquez, Llu\'{i}s and
	    Atanasova, Pepa and
	    Zaghouani, Wajdi and
	    Kyuchukov, Spas and
	    Da San Martino, Giovanni and
	    Nakov, Preslav",
    title     = "Overview of the {CLEF-2018 CheckThat}! Lab on Automatic Identification and Verification of Political Claims, Task 2: Factuality",
    booktitle = "CLEF 2018 Working Notes. Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum (CLEF'18)",
    series    = "{CEUR} Workshop Proceedings",
    publisher = "CEUR-WS.org",
    editor    = "Cappellato, Linda and Ferro, Nicola and Nie, Jian-Yun and Soulier, Laure",
    address   = "Avignon, France",
    month     = "September",
    url       = "http://ceur-ws.org/Vol-2125/invited_paper_14.pdf",
    year      = "2018",
}

@inproceedings{barron2015factory,
  author="Barr{\'o}n-Cede{\~n}o, Alberto and
	  Espa{\~n}a-Bonet, Cristina and
	  Boldoba, Josu and
	  M{\`a}rquez, Llu{\'\i}s",
  title="{A factory of comparable corpora from Wikipedia}",
  booktitle="Proceedings of the Eighth Workshop on Building and Using Comparable Corpora",
  pages="3--13",
  year="2015"
}

@inproceedings{barron2015thread,
  author="Barr{\'o}n-Cede{\~n}o, Alberto and
	Filice, Simone and
	Da San Martino, Giovanni and
	Joty, Shafiq and
	M{\`a}rquez, Llu{\'i}s and
	Nakov, Preslav and
	Moschitti, Alessandro",
  title="Thread-level information for comment classification in community question answering",
  booktitle="Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
  volume="2",
  pages="687--693",
  year="2015",
  url = "https://aclweb.org/anthology/papers/P/P15/P15-2113/"
}

@inproceedings{barron2018overview,
  author="Barr{\'o}n-Cede{\~n}o, Alberto and
	Elsayed, Tamer and
	Suwaileh, Reem and
	M{\`a}rquez, Llu{\'i}s and
	Atanasova, Pepa and
	Zaghouani, Wajdi and
	Kyuchukov, Spas and
	Da San Martino, Giovanni and
	Nakov, Preslav",
  title="Overview of the CLEF-2018 CheckThat! Lab on automatic identification and verification of political claims. Task 2: Factuality",
  booktitle="Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum",
  year="2018",
  url = "http://ceur-ws.org/Vol-2125/invited_paper_14.pdf"
}

@inproceedings{SeminarUsers2017,
  author    = "Kareem Darwish and
               Dimitar Alexandrov and
               Preslav Nakov and
               Yelena Mejova",
  title     = "Seminar Users in the {A}rabic {T}witter Sphere",
  booktitle = "Proceedings of the 9th International Conference on Social Informatics (SocInfo'17)",
  series    = "SocInfo'17",
  address   = "Oxford, UK",
  pages     = "91--108",
  year      = "2017",
  url       = "http://doi.org/10.1007/978-3-319-67217-5_7",
  doi       = "10.1007/978-3-319-67217-5_7",
}

@article{martino2016addressing,
  author="{Da San Martino}, Giovanni and
	  Barr{\'o}n-Cede{\~n}o, Alberto and
	  Romeo, Salvatore and
	  Moschitti, Alessandro and
	  Joty, Shafiq and
	  Al Obaidli, Fahad A and
	  Tymoshenko, Kateryna and
	  Uva, Antonio",
  title="Addressing Community Question Answering in English and Arabic",
  journal="arXiv preprint arXiv:1610.05522",
  year="2016",
  url="http://disi.unitn.it/moschitti/since2013/2016_SIGIR_Da-San-Martino_CQA-English-Arabic.pdf"
}

@inproceedings{da2016learning,
  author="Da San Martino, Giovanni and
	Barr{\'o}n Cede{\~n}o, Alberto and
	Romeo, Salvatore and
	Uva, Antonio and
	Moschitti, Alessandro",
  title="Learning to re-rank questions in community question answering using advanced features",
  booktitle="Proceedings of the 25th ACM International on Conference on Information and Knowledge Management",
  pages="1997--2000",
  year="2016",
  organization="ACM"
}

@inproceedings{martino2017cross,
  author="Da San Martino, Giovanni and
	Romeo, Salvatore and
	Barr{\'o}n-Cede{\~n}o, Alberto and
	Joty, Shafiq and
	Marquez, Lluis and
	Moschitti, Alessandro and
	Nakov, Preslav",
  title="Cross-language question re-ranking",
  booktitle="Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-2017)",
  year="2017",
  url="https://raihanjoty.github.io/papers/martino-et-al-sigir-17.pdf"
}

@inproceedings{espana-bonet-barron-cedeno-2017-lump,
    title = "Lump at SemEval-2017 Task 1: Towards an Interlingua Semantic Similarity",
    author = "Espa{\~n}a-Bonet, Cristina  and
      Barr{\'o}n-Cede{\~n}o, Alberto",
    booktitle = "Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)",
    month = "August",
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/S17-2019",
    doi = "10.18653/v1/S17-2019",
    pages = "144--149",
}

@article{espana2017empirical,
  title="An empirical analysis of nmt-derived interlingual embeddings and their use in parallel sentence identification",
  author="Espa{\~n}a-Bonet, Cristina and Varga, {\'A}d{\'a}m Csaba and Barr{\'o}n-Cede{\~n}o, Alberto and van Genabith, Josef",
  journal="IEEE Journal of Selected Topics in Signal Processing",
  volume="11",
  number="8",
  pages="1340--1350",
  year="2017",
  publisher="IEEE",
  url= "https://ieeexplore.ieee.org/document/8070942"
}

@article{flores2015cross,
  author="Flores, Enrique and
	Barr{\'o}n-Cede{\~n}o, Alberto and
	Moreno, Lidia and
	Rosso, Paolo",
  title="Cross-Language Source Code Re-Use Detection Using Latent Semantic Analysis",
  journal="J. UCS",
  volume="21",
  number="13",
  pages="1708--1725",
  year="2015",
  url="http://www.jucs.org/jucs_21_13/cross_language_source_code/jucs_21_13_1708_1725_flores.pdf"
}

@article{formiga2015leveraging,
  author="Formiga, Llu{\'\i}s and
	  Barr{\'o}n-Cede\~no, Alberto and
	  M{\`a}rquez, Llu{\'i}s and
	  Henr{\'\i}quez, Carlos A. and
	  Mari{\~n}o, Jos{\'e} B.",
  title="Leveraging online user feedback to improve statistical machine translation",
  journal="Journal of Artificial Intelligence Research",
  volume="54",
  pages="159--192",
  year="2015",
  url = "https://dl.acm.org/citation.cfm?id=2910562"
}

@inproceedings{RANLP2017:debates,
  author="Pepa Gencheva and
	Preslav Nakov and
	Llu\'{i}s M\`{a}rquez and
	Alberto Barr\'on-Cede{\~n}o and
	Ivan Koychev",
  title="A Context-Aware Approach for Detecting Worth-Checking Claims in Political Debates",
  booktitle="Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP'17)",
  series = "RANLP'17",
  address = "Varna, Bulgaria",
  pages = "267--276",
  year="2017",
  url="http://doi.org/10.26615/978-954-452-049-6_037",
}

@inproceedings{hoque-etal-2016-interactive,
    title = "An Interactive System for Exploring Community Question Answering Forums",
    author = "Hoque, Enamul  and
      Joty, Shafiq  and
      M{\`a}rquez, Llu{\'\i}s  and
      Barr{\'o}n-Cede{\~n}o, Alberto  and
      Da San Martino, Giovanni  and
      Moschitti, Alessandro  and
      Nakov, Preslav  and
      Romeo, Salvatore  and
      Carenini, Giuseppe",
    booktitle = "Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations",
    month = "December",
    year = "2016",
    address = "Osaka, Japan",
    publisher = "The COLING 2016 Organizing Committee",
    url = "https://www.aclweb.org/anthology/C16-2001",
    pages = "1--5",
}

@InProceedings{NAACL2018:claimrank,
  author    = "Jaradat, Israa and
	Gencheva, Pepa and
	Barr\'on-Cede{\~n}o, Alberto and
	M\`{a}rquez, Llu\'{i}s and
	Nakov, Preslav",
  title     = "{ClaimRank}: Detecting Check-Worthy Claims in {A}rabic and {E}nglish",
  booktitle = "Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT'18)",
  series    = "NAACL-HLT'18",
  year      = "2018",
  pages     = "26-30",
  address   = "New Orleans, LA",
  month     = "June",
  url     = "http://aclweb.org/anthology/N18-5006"
}

@inproceedings{jaradat-etal-2018-claimrank,
    title = "ClaimRank: Detecting Check-Worthy Claims in Arabic and English",
    author = "Jaradat, Israa  and
      Gencheva, Pepa  and
      Barr{\'o}n-Cede{\~n}o, Alberto  and
      M{\`a}rquez, Llu{\'\i}s  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations",
    month = "June",
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/N18-5006",
    doi = "10.18653/v1/N18-5006",
    pages = "26--30",
}

@inproceedings{joty-etal-2015-global,
    title = "Global Thread-level Inference for Comment Classification in Community Question Answering",
    author = "Joty, Shafiq  and
      Barr{\'o}n-Cede{\~n}o, Alberto  and
      Da San Martino, Giovanni  and
      Filice, Simone  and
      M{\`a}rquez, Llu{\'\i}s  and
      Moschitti, Alessandro  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing",
    month = "September",
    year = "2015",
    address = "Lisbon, Portugal",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D15-1068",
    doi = "10.18653/v1/D15-1068",
    pages = "573--578",
}

@inproceedings{RANLP2017:factchecking:external,
  author="Georgi Karadzhov and
	Preslav Nakov and
	Llu\'{i}s M\`{a}rquez and
	Alberto Barr\'on-Cede{\~n}o and
	Ivan Koychev",
  title="Fully Automated Fact Checking Using External Sources",
  booktitle="Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP'17)",
  series = "RANLP'17",
  address = "Varna, Bulgaria",
  year="2017",
  pages     = "344--353",
  URL="http://doi.org/10.26615/978-954-452-049-6_046"
}


@article{InternetResearchJournal:2018,
  author    = "Mihaylov, Todor and
	  Mihaylova, Tsvetomila and
	  Nakov, Preslav and
	  M\`{a}rquez, Llu\'{i}s and
	  Georgiev, Georgi and
	  Koychev, Ivan",
  title     = "The Dark Side of News Community Forums: Opinion Manipulation Trolls",
  journal   = "Internet Research",
  year      = "2018",
  volume    = "28",
  number    = "5",
  pages     = "1292--1312",
  url       = "http://doi.org/10.1108/IntR-03-2017-0118",
  doi       = "10.1108/IntR-03-2017-0118"
}

@InProceedings{AAAI2018:factchecking,
  author    = "Tsvetomila Mihaylova and
	  Preslav Nakov and
	  Llu\'{i}s M\`{a}rquez and
	  Alberto Barr\'on-Cede{\~n}o and
	  Mitra Mohtarami and
	  Georgi Karadjov and
	  James Glass",
  title     = "Fact Checking in Community Forums",
  booktitle = "Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI'18)",
  series    = "AAAI'18",
  year      = "2018",
  address   = "New Orleans, LA",
  pages     = "5309--5316",
  month     = "February",
  url     = "https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewFile/16780/16082"
}


@InProceedings{clef2018checkthat:overall,
    author    = "Nakov, Preslav and
	    Barr\'{o}n-Cede\~{n}o, Alberto and
	    Elsayed, Tamer and
	    Suwaileh, Reem and
	    M\`{a}rquez, Llu\'{i}s and
	    Zaghouani, Wajdi and
	    Atanasova, Pepa and
	    Kyuchukov, Spas and
	    Da San Martino, Giovanni",
    title     = "Overview of the {CLEF}-2018 {CheckThat}! Lab on Automatic Identification and Verification of Political Claims",
    booktitle = "Proceedings of the Ninth International Conference of the CLEF Association: Experimental IR Meets Multilinguality, Multimodality, and Interaction (CLEF'18)",
    series    = "Lecture Notes in Computer Science",
    publisher = "Springer",
    editor    = "Patrice Bellot, Chiraz Trabelsi, Josiane Mothe, Fionn Murtagh, Jian Yun Nie, Laure Soulier, Eric Sanjuan, Linda Cappellato, Nicola Ferro",
    address   = "Avignon, France",
    month     = "September",
    year      = "2018",
    pages     = "372--387",
    url       = "http://link.springer.com/chapter/10.1007/978-3-319-98932-7_32"
}

@article{JDIQ2019,
    author    = "Preslav Nakov and
	  M\`{a}rquez, Llu\'{i}­s and
	  Barr\'{o}n-Cede\~{n}o, Alberto and
	  Pepa Gencheva and
	  Georgi Karadzhov and
	  Tsvetomila Mihaylova and
	  Mitra Mohtarami and
	  James Glass",
    title     = "Automatic Fact Checking Using Context and Discourse Information",
    journal   = "ACM Journal of Data and Information Quality (ACM JDIQ)",
    year      = "2019",
}

@inproceedings{RANLP2017:credibility:trolls,
  author="Preslav Nakov and
	Tsvetomila Mihaylova and
	Llu\'is M\`arquez and
	Yashkumar Shiroya and
	Ivan Koychev",
  title="Do Not Trust the Trolls: Predicting Credibility in Community Question Answering Forums",
  booktitle="Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP'17)",
  series = "RANLP'17",
  address = "Varna, Bulgaria",
  year="2017",
  pages     = "551--560",
  url="http://doi.org/10.26615/978-954-452-049-6_072",
}

@inproceedings{nicosia-etal-2015-qcri,
    title = "QCRI: Answer Selection for Community Question Answering - Experiments for Arabic and English",
    author = "Nicosia, Massimo  and
      Filice, Simone  and
      Barr{\'o}n-Cede{\~n}o, Alberto  and
      Saleh, Iman  and
      Mubarak, Hamdy  and
      Gao, Wei  and
      Nakov, Preslav  and
      Da San Martino, Giovanni  and
      Moschitti, Alessandro  and
      Darwish, Kareem  and
      M{\`a}rquez, Llu{\'\i}s  and
      Joty, Shafiq  and
      Magdy, Walid",
    booktitle = "Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)",
    month = "June",
    year = "2015",
    address = "Denver, Colorado",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/S15-2036",
    doi = "10.18653/v1/S15-2036",
    pages = "203--209",
}

@inproceedings{romeo2017multiple,
  author="Romeo, Salvatore and
	  Da San Martino, Giovanni and
	  Barr{\'o}n-Cede{\~n}o, Alberto and
	  Moschitti, Alessandro",
  title="A Multiple-Instance Learning Approach to Sentence Selection for Question Ranking",
  booktitle="European Conference on Information Retrieval",
  pages="437--449",
  year="2017",
  organization="Springer, Cham"
}


@inproceedings{romeo-etal-2018-flexible,
    title = "A Flexible, Efficient and Accurate Framework for Community Question Answering Pipelines",
    author = "Romeo, Salvatore  and
      Da San Martino, Giovanni  and
      Barr{\'o}n-Cede{\~n}o, Alberto  and
      Moschitti, Alessandro",
    booktitle = "Proceedings of ACL 2018, System Demonstrations",
    month={July},
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P18-4023",
    pages = "134--139",
}



@InProceedings{clef-checkthat-T1:2019,
    author = {Pepa Atanasova and Preslav Nakov and Georgi Karadzhov and Mitra Mohtarami and Giovanni Da San Martino},
    title  = {Overview of the {CLEF-2019 CheckThat! Lab on Automatic Identification and Verification of Claims. Task 1: Check-Worthiness}},
    booktitle = {CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum (CLEF'19)},
    series    = {{CEUR} Workshop Proceedings},
    publisher = {CEUR-WS.org},
    editor    = {Cappellato, L. and Ferro, N. and Losada, D.E. and M\"uller, H. },
    address   = {Lugano, Switzerland},
    month     = {September},
    year = {2019},
}

@InProceedings{clef-checkthat-T2:2019,
    author = {Hasanain, Maram and Suwaileh, Reem and Elsayed, Tamer and Barr\'{o}n-Cede{\~n}o, Alberto and Nakov, Preslav},
    title  = {Overview of the {CLEF-2019 CheckThat! Lab on Automatic Identification and Verification of Claims. Task 2: Evidence and Factuality}},
    booktitle = {CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum (CLEF'19)},
    series    = {{CEUR} Workshop Proceedings},
    publisher = {CEUR-WS.org},
    editor    = {Cappellato, L. and Ferro, N. and Losada, D.E. and M\"uller, H. },
    address   = {Lugano, Switzerland},
    month     = {September},
    year = {2019},
}



@inproceedings{mihaylova-etal-2019-semeval,
    title = "{S}em{E}val-2019 Task 8: Fact Checking in Community Question Answering Forums",
    author = "Mihaylova, Tsvetomila  and
      Karadzhov, Georgi  and
      Atanasova, Pepa  and
      Baly, Ramy  and
      Mohtarami, Mitra  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval'19)",
    series = {SemEval~'19},
    month = {June},
    year = "2019",
    address = "Minneapolis, Minnesota, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/S19-2149",
    pages = "860--869",
}

@InProceedings{OffenseEval:SemEval:2019,
  author    = {Marcos Zampieri and Shervin Malmasi and Preslav Nakov and Sara Rosenthal and Noura Farra and Ritesh Kumar},
  title     = {{SemEval}-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media ({OffensEval})},
  booktitle = {Proceedings of the International Workshop on Semantic Evaluation (SemEval'19)},
  series    = {SemEval~'19},
  year      = {2019},
  pages = {75--86},
  publisher =   "Association for Computational Linguistics",
  address =  "Minneapolis, MN, USA",
  url = {https://www.aclweb.org/anthology/S19-2010}
}

@inproceedings{shaprin-etal-2019-team,
    title = "Team Jack Ryder at {S}em{E}val-2019 Task 4: Using {BERT} Representations for Detecting Hyperpartisan News",
    author = "Shaprin, Daniel  and
      Da San Martino, Giovanni  and
      Barr{\'o}n-Cede{\~n}o, Alberto  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval'19)",
    series = {SemEval~'19},
    month = {June},
    year = "2019",
    address = "Minneapolis, Minnesota, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/S19-2176",
    pages = "1012--1015",
}

@inproceedings{saleh-etal-2019-team,
    title = "Team {QCRI}-{MIT} at {S}em{E}val-2019 Task 4: Propaganda Analysis Meets Hyperpartisan News Detection",
    author = "Saleh, Abdelrhman  and
      Baly, Ramy  and
      Barr{\'o}n-Cede{\~n}o, Alberto  and
      Da San Martino, Giovanni  and
      Mohtarami, Mitra  and
      Nakov, Preslav  and
      Glass, James",
    booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval'19)",
    series = {SemEval~'19},
    month = {June},
    year = "2019",
    address = "Minneapolis, Minnesota, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/S19-2182",
    pages = "1041--1046",
}



@inproceedings{RANLP2017:clickbait,
  title={We Built a Fake News \& Click-bait Filter: What Happened Next Will Blow Your Mind!},
  author={Georgi Karadzhov and Pepa Gencheva and Preslav Nakov and Ivan Koychev},
  booktitle={Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP'17)},
  series = {RANLP~'17},
  address = {Varna, Bulgaria},
  pages = {334--343},
  year={2017},
  URL="https://www.aclweb.org/anthology/papers/R/R17/R17-1045/"
}


@Inproceedings{Hardalov2016,
author="Hardalov, Momchil
and Koychev, Ivan
and Nakov, Preslav",
editor="Dichev, Christo and Agre, Gennady",
title="In Search of Credible News",
bookTitle="Proceedings of the 17th International Conference on Artificial Intelligence: Methodology, Systems, and Applications",
series = {AIMSA~'16},
address = {Varna, Bulgaria},
year="2016",
publisher="Springer International Publishing",
pages="172--180",
isbn="978-3-319-44748-3",
doi="10.1007/978-3-319-44748-3_17",
url="https://doi.org/10.1007/978-3-319-44748-3_17",
}


@InProceedings{mihaylov-nakov:2016:P16-2,
  author    = {Mihaylov, Todor  and  Nakov, Preslav},
  title     = {Hunting for troll comments in news community forums},
  booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics},
  series    = {ACL~'16},
  month     = {August},
  year      = {2016},
  address   = {Berlin, Germany},
  pages     = {399--405},
  url       = {http://anthology.aclweb.org/P16-2065}
}

@inproceedings{Mihaylov2015FindingOM,
  author    = {Mihaylov, Todor  and  Georgiev, Georgi  and  Nakov, Preslav},
  title     = {Finding opinion manipulation trolls in news community forums},
  booktitle = {Proceedings of the Nineteenth Conference on Computational Natural Language Learning},
  series = {CoNLL~'15},
  month     = {July},
  year      = {2015},
  address   = {Beijing, China},
  pages     = {310--314},
  url       = {http://www.aclweb.org/anthology/K15-1032}
}


@inproceedings{Mihaylov2015ExposingPO,
  author    = {Mihaylov, Todor  and  Koychev, Ivan  and  Georgiev, Georgi  and  Nakov, Preslav},
  title     = {Exposing paid opinion manipulation trolls},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing},
  series = {RANLP~'15},
  month     = {September},
  year      = {2015},
  address   = {Hissar, Bulgaria},
  publisher = {INCOMA Ltd. Shoumen, BULGARIA},
  pages     = {443--450},
  url       = {http://www.aclweb.org/anthology/R15-1058}
}


@InProceedings{SemEval2016:task3:SemanticZ,
  author    = {Todor Mihaylov and Preslav Nakov},
  title     = {{SemanticZ at SemEval-2016 Task 3}: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings},
  booktitle = {Proceedings of the 10th International Workshop on Semantic Evaluation},
  series    = {SemEval~'16},
  year      = {2016},
  address   = {San Diego, California, USA},
  pages     = {879--886},
}

@article{dangovski-etal-2019-rotational,
    title = "Rotational Unit of Memory: A Novel Representation Unit for {RNN}s with Scalable Applications",
    author = "Dangovski, Rumen  and
      Jing, Li  and
      Nakov, Preslav  and
      Tatalovi{\'c}, Mi{\'c}o  and
      Solja{\v{c}}i{\'c}, Marin",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "7",
    month = {March},
    year = "2019",
    url = "https://www.aclweb.org/anthology/Q19-1008",
    doi = "10.1162/tacl_a_00258",
    pages = "121--138",
 }


@inproceedings{durrani-etal-2019-one,
    title = "One Size Does Not Fit All: Comparing {NMT} Representations of Different Granularities",
    author = "Durrani, Nadir  and
      Dalvi, Fahim  and
      Sajjad, Hassan  and
      Belinkov, Yonatan  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = {June},
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/N19-1154",
    pages = "1504--1516",

}


@inproceedings{romeo-etal-2016-neural,
    title = "Neural Attention for Learning to Rank Questions in Community Question Answering",
    author = "Romeo, Salvatore  and
      Da San Martino, Giovanni  and
      Barr{\'o}n-Cede{\~n}o, Alberto  and
      Moschitti, Alessandro  and
      Belinkov, Yonatan  and
      Hsu, Wei-Ning  and
      Zhang, Yu  and
      Mohtarami, Mitra  and
      Glass, James",
    booktitle = "Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
    month = "December",
    year = "2016",
    address = "Osaka, Japan",
    publisher = "The COLING 2016 Organizing Committee",
    url = "https://www.aclweb.org/anthology/C16-1163",
    pages = "1734--1745"
}


      Moschitti, Alessandro",
    booktitle = "Proceedings of ACL 2018, System Demonstrations",
    month = "July",
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P18-4023",
    pages = "134--139",
}


@article{saleh2019team,
  title="Team QCRI-MIT at SemEval-2019 Task 4: Propaganda Analysis Meets Hyperpartisan News Detection",
  author="Saleh, Abdelrhman and Baly, Ramy and Barr{\'o}n-Cede{\~n}o, Alberto and Martino, Giovanni Da San and Mohtarami, Mitra and Nakov, Preslav and Glass, James",
  journal="arXiv preprint arXiv:1904.03513",
  year="2019"
}

@inproceedings{Staykovski:19,
  author="Staykovski, Todor and
              Barr\'{o}n-Cede{\~n}o, Alberto and
              Da San Martino, Giovanni  and
              Nakov, Preslav",
  title="Dense vs. Sparse Representations for News Stream Clustering",
  booktitle="Proceedings of the Second International Workshop on Narrative Extraction from Texts (Text2story)",
  address = "Cologne, Germany",
  year="2019"
}

@inproceedings{abdelali2013toward,
  title={Toward An Efficient Arabic Part of Speech Tagger},
  author={Abdelali, Ahmed and Elhadj, Yahya O Mohamed and Bouziane, Rachid},
  booktitle={2013 ACS International Conference on Computer Systems and Applications (AICCSA)},
  pages={1--1},
  year={2013},
  organization={IEEE}
}

@inproceedings{sajjad2013qcri,
  title={QCRI at IWSLT 2013: Experiments in Arabic-English and English-Arabic Spoken Language Translation},
  author={Sajjad, Hassan and Guzm{\'a}n, Francisco and Nakov, Preslav and Abdelali, Ahmed and Murray, Kenton and Al Obaidli, Fahad and Vogel, Stephan},
  booktitle={IWSLT 2013},
  year={2013}
}

@inproceedings{guzman2013amara,
  title={The AMARA corpus: Building resources for translating the web’s educational content},
  author={Guzman, Francisco and Sajjad, Hassan and Vogel, Stephan and Abdelali, Ahmed},
  booktitle={Proceedings of the International Workshop on Spoken Language Translation, IWSLT},
  volume={13},
  year={2013}
}

@inproceedings{tourani2014strategy,
  title={Strategy Stories of Annual Reports: Case of Sears Canada Incorporation},
  author={Tourani, Nazanin and Abdelali, Ahmed},
  booktitle={Society of Business Research Conference - March 20-22, 2014, Phoenix AZ.},
  year={2014}
}

@inproceedings{darwish2014using,
  title={Using Stem-Templates to Improve Arabic POS and Gender/Number Tagging.},
  author={Darwish, Kareem and Abdelali, Ahmed and Mubarak, Hamdy},
  booktitle={LREC},
  pages={2926--2931},
  year={2014}
}

@inproceedings{abdelali2014amara,
  title={The AMARA Corpus: Building Parallel Language Resources for the Educational Domain.},
  author={Abdelali, Ahmed and Guzman, Francisco and Sajjad, Hassan and Vogel, Stephan},
  booktitle={LREC},
  volume={14},
  pages={1044--1054},
  year={2014}
}


@inproceedings{mahmoud2014translation,
  title={Translation And Transcription Of Educational Videos},
  author={Mahmoud, Ba, Elsherif and Vashist, Arushi and Temnikova, Irina and Abdelali, Ahmed and Guzm{\'a}n, Francisco},
  booktitle={Qatar Foundation Annual Research Conference},
  number={1},
  pages={ITSP1067},
  year={2014}
}


@article{sajjad2015qcn,
  title={QCN System Description for NIST OpenMT15},
  author={Sajjad, Hassan and Durrani, Nadir and Guzman, Francisco and Nakov, Preslav and Abdelali, Ahmed and Vogel, Stephan and Salloum, Wael and El Kholy, Ahmed and Habash, Nizar},
  year={2015}
}

@inproceedings{elhadj2014revisiting,
  title={Revisiting Arabic part of speech tagsets},
  author={Elhadj, Yahya OM and Abdelali, Ahmed and Bouziane, Rachid and Ammar, Adel H},
  booktitle={2014 IEEE/ACS 11th International Conference on Computer Systems and Applications (AICCSA)},
  pages={793--802},
  year={2014},
  organization={IEEE}
}

@inproceedings{darwish2014query,
  title={Query Term Expansion by Automatic Learning of  Morphological Equivalence Patterns from Wikipedia},
  author={Darwish, Kareem and Ali, Ahmed M. and Abdelali, Ahmed},
  booktitle={SIGIR 2014 Workshop on Semantic Matching in Information Retrieval (SMIR)},
  volume={1204},
  pages={24--29},
  year={2014},
  organization={CEUR-WS}
}

@inproceedings{sajjad2015qcn,
  title={The QCN Egyptian Arabic to English Statistical Machine Translation System for NIST OpenMT’2015},
  author={Sajjad, Hassan and Durrani, Nadir and Guzman, Francisco and Nakov, Preslav and Abdelali, Ahmed and Vogel, Stephan and Salloum, Wael and El Kholy, Ahmed and Habash, Nizar},
  booktitle={OpenMT’2015},
  year={2015}
}

@inproceedings{abdelali2015qat2,
  title={QAT2—The QCRI Advanced Transcription and Translation System},
  author={Abdelali, Ahmed and Ali, Ahmed and Guzm{\'a}n, Francisco and Stahlberg, Felix and Vogel, Stephan and Zhang, Yifan},
  booktitle={Sixteenth Annual Conference of the International Speech Communication Association},
  year={2015}
}

@inproceedings{mubarak2015qcri,
  title={QCRI $@$ QALB-2015 Shared Task: Correction of Arabic Text for Native and Non-Native Speakers’ Errors},
  author={Mubarak, Hamdy and Darwish, Kareem and Abdelali, Ahmed},
  booktitle={Proceedings of the Second Workshop on Arabic Natural Language Processing},
  pages={150--154},
  year={2015}
}

@inproceedings{shafiq2015avoid,
  title={How to Avoid Unwanted Pregnancies: Domain Adaptation using Neural Network Models},
  author={Shafiq Joty, Hassan Sajjad and Durrani, Nadir and Al-Mannai, Kamla and Abdelali, Ahmed and Vogel, Stephan},
  booktitle={EMNLP},
  year={2015}
}


@article{doumi2016semi,
  title={A Semi-Automatic and Low Cost Approach to Build Scalable Lemma-based Lexical Resources for Arabic Verbs},
  author={Doumi, Noureddine and Lehireche, Ahmed and Maurel, Denis and Abdelali, Ahmed},
  journal={International Journal of Information Technology and Computer Science (IJITCS)},
  volume={8},
  number={1},
  year={2016}
}

@inproceedings{francisco2015humans,
  title={How do Humans Evaluate Machine Translation},
  author={Francisco, Guzm{\'a}n and Abdelali, Ahmed and Temnikova, Irina and Sajjad, Hassan and Vogel, Stephan},
  booktitle={Proceedings of the Tenth Workshop on Statistical Machine Translation. Lisboa, Portugal},
  pages={457--466},
  year={2015},
  organization={Association for Computational Linguistics}
}

@inproceedings{sajjad2016eyes,
  title={Eyes Don't Lie: Predicting Machine Translation Quality Using Eye Movement},
  author={Sajjad, Hassan and Guzm{\'a}n, Francisco and Durrani, Nadir and Abdelali, Ahmed and Bouamor, Houda and Temnikova, Irina and Vogel, Stephan},
  booktitle={Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  pages={1082--1088},
  year={2016}
}

@inproceedings{abdelali2016iappraise,
  title={iAppraise: A Manual Machine Translation Evaluation Environment},
  author={Abdelali, Ahmed and Durrani, Nadir and Guzm{\'a}n, Francisco},
  booktitle={Proceedings of NAACL-HLT 2016 (Demonstrations)},
  pages={17--21},
  year={2016},
  organization={Association for Computational Linguistics}
}

@inproceedings{mubarak2016arabic,
  title={Arabic to English Person Name Transliteration using Twitter},
  author={Mubarak, Hamdy and Abdelali, Ahmed},
  booktitle={Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
  pages={351--355},
  year={2016},
  organization={European Language Resources Association (ELRA)}
}

@misc{hacker2014analyzng,
  title={Analyzng iranian leaders’ conflict framing with Leximancer Atomated Text Analysis},
  author={Hacker, Kenneth L and Abdelali, Ahmed and Johnston, Jennifer and Boje, David},
  year={2014},
  publisher={Progress}
}

@article{darwish2017arabic,
  title={Arabic POS Tagging: Don’t Abandon Feature Engineering Just Yet},
  author={Darwish, Kareem and Mubarak, Hamdy and Abdelali, Ahmed and Eldesouki, Mohamed},
  journal={WANLP 2017 (co-located with EACL 2017)},
  pages={130},
  year={2017}
}


@misc{abdelali2017query,
  title={Query expansion system and method using language and language variants},
  author={Abdelali, Ahmed},
  year={2017},
  month={may},
  note={US Patent App. 15/117,107}
}

@inproceedings{parsing2016natural,
  title={Natural language processing},
  author={Parsing, Dependency},
  booktitle={Proceedings of the ACL Workshop on Statistical NLP and Weighted Automata (StatFSM)},
  pages={32--41},
  year={2016}
}


@article{sajjad2017challenging,
  title={Challenging language-dependent segmentation for arabic: An application to machine translation and part-of-speech tagging},
  author={Sajjad, Hassan and Dalvi, Fahim and Durrani, Nadir and Abdelali, Ahmed and Belinkov, Yonatan and Vogel, Stephan},
  journal={arXiv preprint arXiv:1709.00616},
  year={2017}
}


@article{temnikova2017interpreting,
  title={Interpreting strategies annotation in the WAW corpus},
  author={Temnikova, Irina and Abdelali, Ahmed and Hedaya, Samy and Vogel, Stephan and Al Daher, Aishah},
  journal={RANLP 2017},
  pages={36},
  year={2017}
}

@article{bougrine2017altruistic,
  title={Altruistic crowdsourcing for arabic speech corpus annotation},
  author={Bougrine, Soumia and Cherroun, Hadda and Abdelali, Ahmed},
  journal={Procedia Computer Science},
  volume={117},
  pages={137--144},
  year={2017},
  publisher={Elsevier}
}

@inproceedings{abdelali2018waw,
  title={The WAW Corpus: The First Corpus of Interpreted Speeches and Their Translations for English and Arabic.},
  author={Abdelali, Ahmed and Temnikova, Irina and Hedaya, Samy and Vogel, Stephan},
  booktitle={Language Resources and Evaluation Conference (LREC 2018)},
  pages={2135--2140},
  year={2018},
  organization={Miyazaki, Japan.}
}

@inproceedings{darwish2018diacritization,
  title={Diacritization of Moroccan and Tunisian Arabic Dialects: A CRF Approach},
  author={Darwish, Kareem and Abdelali, Ahmed and Mubarak, Hamdy and Samih, Younes and Attia, Mohammed},
  booktitle={Proceedings of The 4th Arabic Natural Language Processing Workshop (WANLP-2018),  the 11th edition of the Language Resources and Evaluation Conference},
  year={2018},
  organization={Miyazaki (Japan).}
}

@inproceedings{darwish2018multi,
  title={Multi-Dialect Arabic POS Tagging: A CRF Approach},
  author={Darwish, Kareem and Mubarak, Hamdy and Abdelali, Ahmed and Eldesouki, Mohamed and Samih, Younes and Alharbi, Randah and Attia, Mohammed and Magdy, Walid and Kallmeyer, Laura},
  booktitle={In 11th edition of the Language Resources and Evaluation Conference},
  year={2018},
  organization={Miyazaki (Japan).}
}

@inproceedings{hadda2018spoken,
  title={Spoken Arabic Algerian dialect identification},
  author={Hadda, Cherroun and Bougrine, Soumia and Abdelali, Ahmed},
  booktitle={Natural Language and Speech Processing (ICNLSP), 2018 2nd International Conference on},
  pages={1--6},
  year={2018},
  organization={IEEE}
}


@inproceedings{alharbi-etal-2018-part,
    title = "Part-of-Speech Tagging for {A}rabic {G}ulf Dialect Using {B}i-{LSTM}",
    author = "Alharbi, Randah  and
      Magdy, Walid  and
      Darwish, Kareem  and
      AbdelAli, Ahmed  and
      Mubarak, Hamdy",
    booktitle = "Proceedings of the Eleventh International Conference on Language Resources and Evaluation ({LREC} 2018)",
    month = {may},
    year = "2018",
    address = "Miyazaki, Japan",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://www.aclweb.org/anthology/L18-1620",
}

@inproceedings{hefny2011query,
  title={Is a query worth translating: ask the users!},
  author={Hefny, Ahmed and Darwish, Kareem and Alkahky, Ali},
  booktitle={European Conference on Information Retrieval},
  pages={238--250},
  year={2011},
  organization={Springer, Berlin, Heidelberg}
}

@inproceedings{el2011improved,
  title={Improved transliteration mining using graph reinforcement},
  author={El-Kahky, Ali and Darwish, Kareem and Aldein, Ahmed Saad and El-Wahab, Mohamed Abd and Hefny, Ahmed and Ammar, Waleed},
  booktitle={Proceedings of the Conference on Empirical Methods in Natural Language Processing},
  pages={1384--1393},
  year={2011},
  organization={Association for Computational Linguistics}
}

@inproceedings{el2012transliteration,
  title={Transliteration mining using large training and test sets},
  author={El Kahki, Ali and Darwish, Kareem and Abdul-Wahab, Mohamed and Taei, Ahmed},
  booktitle={Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  pages={243--252},
  year={2012}
}

@inproceedings{darwish2012arabic,
  title={Arabic retrieval revisited: Morphological hole filling},
  author={Darwish, Kareem and Ali, Ahmed},
  booktitle={Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  pages={218--222},
  year={2012}
}

@inproceedings{moussa2012statistical,
  title={Statistical denormalization for Arabic text.},
  author={Moussa, Mohammed and Fakhr, Mohammed and Darwish, Kareem},
  booktitle={KONVENS},
  pages={228--232},
  year={2012}
}

@inproceedings{darwish2012language,
  title={Language processing for arabic microblog retrieval},
  author={Darwish, Kareem and Magdy, Walid and Mourad, Ahmed},
  booktitle={Proceedings of the 21st ACM international conference on Information and knowledge management},
  pages={2427--2430},
  year={2012}
}

@inproceedings{gao2012joint,
  title={Joint topic modeling for event summarization across news and social media streams},
  author={Gao, Wei and Li, Peng and Darwish, Kareem},
  booktitle={Proceedings of the 21st ACM international conference on Information and knowledge management},
  pages={1173--1182},
  year={2012}
}

@inproceedings{magdy2012summarization,
  title={A summarization tool for time-sensitive social media},
  author={Magdy, Walid and Ali, Ahmed and Darwish, Kareem},
  booktitle={Proceedings of the 21st ACM international conference on Information and knowledge management},
  pages={2695--2697},
  year={2012}
}

@misc{darwish2013online,
  title={Online communities},
  author={Darwish, Kareem},
  year={2013},
  month="feb",
  note={US Patent App. 13/218,828}
}

@inproceedings{mourad2013subjectivity,
  title={Subjectivity and sentiment analysis of modern standard Arabic and Arabic microblogs},
  author={Mourad, Ahmed and Darwish, Kareem},
  booktitle={Proceedings of the 4th workshop on computational approaches to subjectivity, sentiment and social media analysis},
  pages={55--64},
  year={2013}
}

@misc{ali2013automated,
  title={Automated admission},
  author={Ali, Ahmed and Darwish, Kareem},
  year={2013},
  month="jun",
  note={US Patent App. 13/370,097}
}

@inproceedings{el2011qcri,
  title={QCRI@ TREC 2011: Microblog Track.},
  author={El Kahki, Ali and Darwish, Kareem},
  booktitle={TREC},
  year={2011}
}

@article{darwish2013arabizi,
  title={Arabizi detection and conversion to Arabic},
  author={Darwish, Kareem},
  journal={arXiv preprint arXiv:1306.6755},
  year={2013}
}

@misc{darwish2014arabic,
  title={Arabic Information Retrieval},
  author={Darwish, Kareem and Magdy, Walid},
  journal={Foundations and Trends in Information Retrieval},
  volume={7},
  number={4},
  pages={239--342},
  year={2014},
  publisher={Now Publishers Inc}
}

@inproceedings{sajjad2013translating,
  title={Translating Dialectal Arabic to English},
  author={Sajjad, Hassan and Darwish, Kareem and Belinkov, Yonatan},
  booktitle={Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  pages={1--6},
  year={2013},
  organization={Association for Computational Linguistics}
}

@inproceedings{darwish2013named,
  title={Named Entity Recognition using Cross-lingual Resources: Arabic as an Example},
  author={Darwish, Kareem},
  booktitle={Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics},
  pages={1558--1567},
  year={2013},
  organization={Association for Computational Linguistics}
}

@incollection{hassan2014statistical,
  title={Statistical machine translation},
  author={Hassan, Hany and Darwish, Kareem},
  booktitle={Natural Language Processing of Semitic Languages},
  pages={199--219},
  year={2014},
  publisher={Springer, Berlin, Heidelberg}
}


@article{kothari2013detecting,
  title={Detecting Comments on News Articles in Microblogs.},
  author={Kothari, Alok and Magdy, Walid and Darwish, Kareem and Mourad, Ahmed and Taei, Ahmed},
  journal={ICWSM},
  volume={2013},
  year={2013}
}


@inproceedings{borge2015content,
  title={Content and network dynamics behind Egyptian political polarization on Twitter},
  author={Borge-Holthoefer, Javier and Magdy, Walid and Darwish, Kareem and Weber, Ingmar},
  booktitle={Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work \& Social Computing},
  pages={700--711},
  year={2015}
}

@inproceedings{darwish2014verifiably,
  title={Verifiably effective arabic dialect identification},
  author={Darwish, Kareem and Sajjad, Hassan and Mubarak, Hamdy},
  booktitle={Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  pages={1465--1468},
  year={2014}
}

@inproceedings{mubarak2014automatic,
  title={Automatic correction of arabic text: a cascaded approach},
  author={Mubarak, Hamdy and Darwish, Kareem},
  booktitle={Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP)},
  pages={132--136},
  year={2014}
}

@inproceedings{mubarak2014using,
  title={Using Twitter to collect a multi-dialectal corpus of Arabic},
  author={Mubarak, Hamdy and Darwish, Kareem},
  booktitle={Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP)},
  pages={1--7},
  year={2014}
}

@inproceedings{borge2014structural,
  title={Structural And Semantic Evolution Of Egyptian Political Polarization On Twitter},
  author={Borge-holthoefer, Javier and Magdy, Walid and Darwish, Kareem and Weber, Ingmar},
  booktitle={Qatar Foundation Annual Research Conference Proceedings Volume 2014 Issue 1},
  volume={2014},
  number={1},
  pages={SSPP0757},
  year={2014},
  organization={Hamad bin Khalifa University Press (HBKU Press)}
}

@article{magdy2015failedrevolutions,
  title={\# failedrevolutions: Using twitter to study the antecedents of isis support},
  author={Magdy, Walid and Darwish, Kareem and Weber, Ingmar},
  journal={arXiv preprint arXiv:1503.02401},
  year={2015}
}

@inproceedings{zhang2015randomized,
  title={Randomized greedy inference for joint segmentation, POS tagging and dependency parsing},
  author={Zhang, Yuan and Li, Chengtao and Barzilay, Regina and Darwish, Kareem},
  booktitle={Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  pages={42--52},
  year={2015}
}

@inproceedings{darwish2014simple,
  title={Simple Effective Microblog Named Entity Recognition: Arabic as an Example},
  author={Darwish, Kareem and Gao, Wei},
  booktitle={International Conference on Language Resources and Evaluation},
  year={2014}
}

@inproceedings{mubarak2015classifying,
  title={Classifying Arab Names Geographically},
  author={Mubarak, Hamdy and Darwish, Kareem},
  booktitle={Proceedings of the Second Workshop on Arabic Natural Language Processing},
  pages={1--8},
  year={2015}
}


@inproceedings{magdy2015like,
  title={" I like ISIS, but I want to watch Chris Nolan's new movie" Exploring ISIS Supporters on Twitter},
  author={Magdy, Walid and Darwish, Kareem and Weber, Ingmar},
  booktitle={Proceedings of the 26th ACM Conference on Hypertext \& Social Media},
  pages={321--322},
  year={2015}
}

@misc{walid2018system,
  title={System and method for automatic generation of information-rich content from multiple microblogs, each microblog containing only sparse information},
  author={Walid, Magdy and Darwish, Kareem and Ali, Ahmed},
  year={2018},
  month="jun",
  note={US Patent 9,990,368}
}

@article{darwish2015attitudes,
  title={Attitudes towards refugees in light of the Paris attacks},
  author={Darwish, Kareem and Magdy, Walid},
  journal={arXiv preprint arXiv:1512.04310},
  year={2015}
}

@article{magdy2015quantifying,
  title={Quantifying public response towards Islam on Twitter after Paris attacks},
  author={Magdy, Walid and Darwish, Kareem and Abokhodair, Norah},
  journal={arXiv preprint arXiv:1512.04570},
  year={2015}
}

@inproceedings{magdy2016isisisnotislam,
  title={\# isisisnotislam or\# deportallmuslims? Predicting unspoken views},
  author={Magdy, Walid and Darwish, Kareem and Abokhodair, Norah and Rahimi, Afshin and Baldwin, Timothy},
  booktitle={Proceedings of the 8th ACM Conference on Web Science},
  pages={95--106},
  year={2016}
}

@inproceedings{abdelali2016farasa,
  title={Farasa: A Fast and Furious Segmenter for Arabic},
  author={Abdelali, Ahmed and Darwish, Kareem and Durrani, Nadir and Mubarak, Hamdy},
  booktitle={15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  pages={11--16},
  year={2016},
  organization={Association for Computational Linguistics}
}

@inproceedings{darwish2016farasa,
  title={Farasa: A New Fast and Accurate Arabic Word Segmenter},
  author={Darwish, Kareem and Mubarak, Hamdy},
  booktitle={Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
  year={2016},
  organization={European Language Resources Association (ELRA)}
}

@article{bensalem2015overview,
  title={Overview of the AraPlagDet PAN@FIRE2015 Shared Task on Arabic Plagiarism Detection},
  author={Bensalem, Imene and Boukhalfa, Imene and Rosso, Paolo and Abouenour, Lahsen and Darwish, Kareem and Chikhi, Salim},
  journal={Notebook Papers of FIRE 2015},
  volume={1587},
  year={2015}
}

@inproceedings{darwish2017barabic,
  title={Arabic Diacritization: Stats, Rules, and Hacks},
  author={Darwish, Kareem and Mubarak, Hamdy and Abdelali, Ahmed},
  booktitle={Proceedings of the Third Arabic Natural Language Processing Workshop},
  pages={9--17},
  year={2017},
  organization={Association for Computational Linguistics}
}

@inproceedings{samih2017neural,
  title={A Neural Architecture for Dialectal Arabic Segmentation},
  author={Samih, Younes and Attia, Mohammed and Eldesouki, Mohamed and Abdelali, Ahmed and Mubarak, Hamdy and Kallmeyer, Laura and Darwish, Kareem},
  booktitle={Proceedings of the Third Arabic Natural Language Processing Workshop},
  pages={46--54},
  year={2017},
  organization={Association for Computational Linguistics}
}

@inproceedings{darwish2017aarabic,
  title={Arabic POS Tagging: Don't Abandon Feature Engineering Just Yet},
  author={Darwish, Kareem and Mubarak, Hamdy and Abdelali, Ahmed and Eldesouki, Mohamed},
  booktitle={Proceedings of the Third Arabic Natural Language Processing Workshop},
  pages={130--137},
  year={2017},
  organization={Association for Computational Linguistics}
}

@inproceedings{darwish2017trump,
  title={Trump vs. Hillary: What went viral during the 2016 US presidential election},
  author={Darwish, Kareem and Magdy, Walid and Zanouda, Tahar},
  booktitle={International conference on social informatics (SocInfo-2017)},
  pages={143--161},
  year={2017},
  organization={Springer, Cham}
}

@inproceedings{darwish2017seminar,
  title={Seminar users in the Arabic Twitter sphere},
  author={Darwish, Kareem and Alexandrov, Dimitar and Nakov, Preslav and Mejova, Yelena},
  booktitle={International Conference on Social Informatics},
  pages={91--108},
  year={2017},
  organization={Springer, Cham}
}

@inproceedings{mubarak2017abusive,
  title={Abusive language detection on Arabic social media},
  author={Mubarak, Hamdy and Darwish, Kareem and Magdy, Walid},
  booktitle={Proceedings of the first workshop on abusive language online},
  pages={52--56},
  year={2017}
}

@inproceedings{samih2017learning,
  title={Learning from relatives: unified dialectal Arabic segmentation},
  author={Samih, Younes and Eldesouki, Mohamed and Attia, Mohammed and Darwish, Kareem and Abdelali, Ahmed and Mubarak, Hamdy and Kallmeyer, Laura},
  booktitle={Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},
  pages={432--441},
  year={2017}
}

@inproceedings{darwish2017improved,
  title={Improved Stance Prediction in a User Similarity Feature Space},
  author={Darwish, Kareem and Magdy, Walid and Zanouda, Tahar},
  booktitle={2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining},
  pages={145--148},
  year={2017},
  organization={Association for Computing Machinery}
}

@article{romeo2019language,
  title={Language processing and learning models for community question answering in arabic},
  author={Romeo, Salvatore and Da San Martino, Giovanni and Belinkov, Yonatan and Barr{\'o}n-Cede{\~n}o, Alberto and Eldesouki, Mohamed and Darwish, Kareem and Mubarak, Hamdy and Glass, James and Moschitti, Alessandro},
  journal={Information Processing \& Management},
  volume={56},
  number={2},
  pages={274--290},
  year={2019},
  publisher={Pergamon}
}

@article{eldesouki2017arabic,
  title={Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM},
  author={Eldesouki, Mohamed and Samih, Younes and Abdelali, Ahmed and Attia, Mohammed and Mubarak, Hamdy and Darwish, Kareem and Laura, Kallmeyer},
  journal={arXiv preprint arXiv:1708.05891},
  year={2017}
}

@inproceedings{habash2017proceedings,
  title={Proceedings of the Third Arabic Natural Language Processing Workshop},
  author={Habash, Nizar and Diab, Mona and Darwish, Kareem and El-Hajj, Wassim and Al-Khalifa, Hend and Bouamor, Houda and Tomeh, Nadi and El-Haj, Mahmoud},
  booktitle={Proceedings of the Third Arabic Natural Language Processing Workshop},
  year={2017}
}

@inproceedings{eldesouki2016qcri,
  title={Qcri@ dsl 2016: Spoken arabic dialect identification using textual features},
  author={Eldesouki, Mohamed and Dalvi, Fahim and Sajjad, Hassan and Darwish, Kareem},
  booktitle={Proceedings of the Third Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial3)},
  pages={221--226},
  year={2016}
}

@inproceedings{habash2015proceedings,
  title={Proceedings of the Second Workshop on Arabic Natural Language Processing},
  author={Habash, Nizar and Vogel, Stephan and Darwish, Kareem},
  booktitle={Proceedings of the Second Workshop on Arabic Natural Language Processing},
  year={2015}
}

@article{darwish2018predicting,
  title={Predicting online islamophobic behavior after\# parisattacks},
  author={Darwish, Kareem and Magdy, Walid and Rahimi, Afshin and Baldwin, Timothy and Abokhodair, Norah},
  journal={The Journal of Web Science},
  volume={4},
  year={2018}
}


@article{kutlu2018devam,
  title={Devam vs. tamam: 2018 Turkish elections},
  author={Kutlu, Mucahid and Darwish, Kareem and Elsayed, Tamer},
  journal={arXiv preprint arXiv:1807.06655},
  year={2018}
}

@article{abdelali2018diacritization,
  title={Diacritization of maghrebi arabic sub-dialects},
  author={Abdelali, Ahmed and Attia, Mohammed and Samih, Younes and Darwish, Kareem and Mubarak, Hamdy},
  journal={arXiv preprint arXiv:1810.06619},
  year={2018}
}

@article{darwish2018kavanaugh,
  title={To kavanaugh or not to kavanaugh: That is the polarizing question},
  author={Darwish, Kareem},
  journal={arXiv preprint arXiv:1810.06687},
  year={2018}
}

@inproceedings{mubarak2016demographic,
  title={Demographic surveys of arab annotators on crowdflower},
  author={Mubarak, Hamdy and Darwish, Kareem},
  booktitle={Weaving Relations of Trust in Crowd Work: Transparency and Reputation across Platforms Workshop},
  year={2016}
}


@inproceedings{mubarak2019highly,
  title={Highly effective arabic diacritization using sequence to sequence modeling},
  author={Mubarak, Hamdy and Abdelali, Ahmed and Sajjad, Hassan and Samih, Younes and Darwish, Kareem},
  booktitle={Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)},
  pages={2390--2395},
  year={2019}
}

@article{stefanov2019predicting,
  title={Predicting the topical stance of media and popular twitter users},
  author={Stefanov, Peter and Darwish, Kareem and Atanasov, Atanas and Nakov, Preslav},
  journal={arXiv preprint arXiv:1907.01260},
  year={2019}
}

@inproceedings{samih2019qc,
  title={QC-GO Submission for MADAR Shared Task: Arabic Fine-Grained Dialect Identification},
  author={Samih, Younes and Mubarak, Hamdy and Abdelali, Ahmed and Attia, Mohammed and Eldesouki, Mohamed and Darwish, Kareem},
  booktitle={Proceedings of the Fourth Arabic Natural Language Processing Workshop},
  pages={290--294},
  year={2019}
}

@inproceedings{attia2019pos,
  title={POS Tagging for Improving Code-Switching Identification in Arabic},
  author={Attia, Mohammed and Samih, Younes and Elkahky, Ali and Mubarak, Hamdy and Abdelali, Ahmed and Darwish, Kareem},
  booktitle={Proceedings of the Fourth Arabic Natural Language Processing Workshop},
  pages={18--29},
  year={2019}
}

@inproceedings{eldesouki2019farspeech,
  title={FarSpeech: Arabic Natural Language Processing for Live Arabic Speech.},
  author={Eldesouki, Mohamed and Gopee, Naassih and Ali, Ahmed and Darwish, Kareem},
  booktitle={INTERSPEECH},
  pages={2372--2373},
  year={2019}
}

@article{kutlu2019embedding,
  title={Embedding-based Qualitative Analysis of Polarization in Turkey},
  author={Kutlu, Mucahid and Darwish, Kareem and Bayrak, Cansin and Rashed, Ammar and Elsayed, Tamer},
  journal={arXiv preprint arXiv:1909.10213},
  year={2019}
}


@inproceedings{mubarak2019system,
  title={A System for Diacritizing Four Varieties of Arabic},
  author={Mubarak, Hamdy and Abdelali, Ahmed and Darwish, Kareem and Eldesouki, Mohamed and Samih, Younes and Sajjad, Hassan},
  booktitle={Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations},
  pages={217--222},
  year={2019}
}

@inproceedings{darwish2019quantifying,
  title={Quantifying polarization on twitter: The kavanaugh nomination},
  author={Darwish, Kareem},
  booktitle={International Conference on Social Informatics (SocInfo-2019)},
  pages={188--201},
  year={2019},
  organization={Springer, Cham}
}

@inproceedings{mubarak2019arabic,
  title={Arabic offensive language classification on twitter},
  author={Mubarak, Hamdy and Darwish, Kareem},
  booktitle={International Conference on Social Informatics},
  pages={269--276},
  year={2019},
  organization={Springer, Cham}
}

@article{darwish2020arabic,
  title={Arabic Diacritic Recovery Using a Feature-Rich biLSTM Model},
  author={Darwish, Kareem and Abdelali, Ahmed and Mubarak, Hamdy and Eldesouki, Mohamed},
  journal={arXiv preprint arXiv:2002.01207},
  year={2020}
}

@article{samih2020few,
  title={A Few Topical Tweets are Enough for Effective User-Level Stance Detection},
  author={Samih, Younes and Darwish, Kareem},
  journal={arXiv preprint arXiv:2004.03485},
  year={2020}
}


@article{darwish2020effective,
  title={Effective Multi Dialectal Arabic POS Tagging},
  author={Darwish, Kareem and Attia, Mohammed and Mubarak, Hamdy and Samih, Younes and Abdelali, Ahmed and M{\`a}rquez, Llu{\'\i}s and Eldesouki, Mohamed and Kallmeyer, Laura},
  journal={Natural Language Engineering},
  volume={1},
  number={1},
  pages={18},
  year={2020},
  publisher={Cambridge University Press}
}

@article{alam2020fighting,
  title={Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society},
  author={Alam, Firoj and Shaar, Shaden and Nikolov, Alex and Mubarak, Hamdy and Martino, Giovanni Da San and Abdelali, Ahmed and Dalvi, Fahim and Durrani, Nadir and Sajjad, Hassan and Darwish, Kareem and others},
  journal={arXiv preprint arXiv:2005.00033},
  year={2020}
}

@article{abdelali2020arabic,
  title={Arabic Dialect Identification in the Wild},
  author={Abdelali, Ahmed and Mubarak, Hamdy and Samih, Younes and Hassan, Sabit and Darwish, Kareem},
  journal={arXiv preprint arXiv:2005.06557},
  year={2020}
}

@article{rashed2020embeddings,
  title={Embeddings-Based Clustering for Target Specific Stances: The Case of a Polarized Turkey},
  author={Rashed, Ammar and Kutlu, Mucahid and Darwish, Kareem and Elsayed, Tamer and Bayrak, Cans{\i}n},
  journal={15th International AAAI Conference on Web and Social Media (ICWSM-2021},
  year={2021}
}

@inproceedings{mubarak2020overview,
  title={Overview of OSACT4 Arabic Offensive Language Detection Shared Task},
  author={Mubarak, Hamdy and Darwish, Kareem and Magdy, Walid and Elsayed, Tamer and Al-Khalifa, Hend},
  booktitle={Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection},
  pages={48--52},
  year={2020}
}

@inproceedings{al2020proceedings,
  title={Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection},
  author={Al-Khalifa, Hend and Magdy, Walid and Darwish, Kareem and Elsayed, Tamer and Mubarak, Hamdy},
  booktitle={Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection},
  year={2020}
}

@misc{weber2019social,
  title={Social Informatics: 11th International Conference, SocInfo 2019, Doha, Qatar, November 18--21, 2019, Proceedings},
  author={Weber, Ingmar and Darwish, Kareem M and Wagner, Claudia and Zagheni, Emilio and Nelson, Laura and Aref, Samin and Fl{\"o}ck, Fabian},
  year={2019},
  publisher={Springer Nature}
}

@article{elalfy2020corporations,
  title={Corporations and sustainable development goals communication on social media: Corporate social responsibility or just another buzzword?},
  author={ElAlfy, Amr and Darwish, Kareem M and Weber, Olaf},
  journal={Sustainable Development},
  year={2020},
  publisher={John Wiley \& Sons, Inc. Chichester, UK}
}

@article{shurafa2020political,
  title={Political Framing: US COVID19 Blame Game},
  author={Shurafa, Chereen and Darwish, Kareem and Zaghouani, Wajdi},
  journal={International Conference on Social Informatics (SocInfo-2020)},
  year={2020}
}

@InProceedings{zaghouani2016normalizing,
  title={Normalizing Mathematical Expressions to Improve the Translation of Educational Content},
  author={Zaghouani, Wajdi and Abdelali, Ahmed and Guzm{\'a}n, Francisco and Sajjad, Hassan},
  booktitle={Proceedings of the AMTA 2016 Workshop Semitic Machine Translation (SeMaT)},
  location = {Austin, US},
  month={October},
  year={2016},
}

@InProceedings{bouamor:bucc18,
author = {Houda Bouamor and Hassan Sajjad},
title = {H2@BUCC18: Parallel Sentence Extraction from Comparable Corpora Using Multilingual Sentence Embeddings},
booktitle = {Proceedings of the 11th Workshop on Building and Using Comparable Corpora (BUCC)},
month = {May},
year = {2018},
location = {Miyzaki, Japan}
}

@InProceedings{sajjad-etal:iwslt17,
author = {Hassan Sajjad and Nadir Durrani and Fahim Dalvi and Yonatan Belinkov and Stephan Vogel},
title = {Neural Machine Translation Training in a Multi-Domain Scenario},
booktitle = {Proceedings of the 14th International Workshop on Spoken Language Translation (IWSLT)},
month = {December},
year = {2017},
location = {Tokyo, Japan}
}


@inproceedings{kamla:anlp2014,
  title={Unsupervised word segmentation improves dialectal {Arabic to English} machine translation},
  author={Al-Mannai, Kamla and Sajjad, Hassan and Khader, Alaa and Al Obaidli, Fahad and Nakov, Preslav and Vogel, Stephan},
  booktitle={Proceedings of the Workshop of Arabic Natural Language Processing (ANLP)},
  year={2014},
  month={October},
  location={Doha, Qatar},

}

@inproceedings{weller13:wmt13,
author = {Marion Weller and Max Kisselew and Svetlana Smekalova and Alexander Fraser and Helmut Schmid and Nadir Durrani and Hassan Sajjad and Richárd Farkas},
title = {{Munich-Edinburgh-Stuttgart Submissions at WMT13: Morphological and Syntactic Processing for SMT}},
booktitle = {Proceedings of the Eighth Workshop on Statistical Machine Translation (WMT)},
year = 2013,
location = {Sofia, Bulgaria},
month = {August},
}

@Inproceedings{durrani-EtAl:2013:WMT,
author = {Nadir Durrani and Helmut Schmid and Alexander Fraser and Hassan Sajjad and Richárd Farkas},
title = {{Munich-Edinburgh-Stuttgart Submissions of OSM Systems at WMT13}},
booktitle = {Proceedings of the Eighth Workshop on Statistical Machine Translation (WMT)},
year = {2013},
month = {August},
location = {Sofia, Bulgaria},

}

@Inproceedings{sajjad-EtAl:2013:WMT,
author = {Sajjad, Hassan and Smekalova, Svetlana and Durrani, Nadir and Fraser, Alexander and Schmid, Helmut},
title = {{QCRI-MES} Submission at {WMT}13: Using Transliteration Mining to Improve Statistical Machine Translation},
booktitle = {Proceedings of the Eighth Workshop on Statistical Machine Translation (WMT)},
year = {2013},
month = {August},
location = {Sofia, Bulgaria},

}

@InProceedings{bouamor:anlp15,
  title={QCMUQ@QALB-2015 Shared Task: Combining Character level MT and Error-tolerant Finite-State Recognition for Arabic
Spelling Correction},
  author={Houda Bouamor and Hassan Sajjad and Nadir Durrani and Kemal Oflazer},
  booktitle={Proceedings of the Workshop of Arabic Natural Language Processing (ANLP)},
  year={2015},
  month={July},
  location={Beijing, China},


}


@InProceedings{sajjad:nist15,
  title={{QCN Egyptian Arabic to English Machine
Translation System for NIST OpenMT15}},
  author={Hassan Sajjad and Nadir Durrani and Francisco Guzman and Preslav Nakov and Ahmed Abdelali and  Stephan Vogel and
Wael Salloum and Ahmed El Kholy and Nizar Habash},
  booktitle={Workshop of NIST OpenMT15},
  location = {Washington DC, US},
  month={June},
  year={2015},
}

@InProceedings{nguyen2016:swdm,
  title={Applications of Online Deep Learning for Crisis Response Using Social Media Information},
  author={Dat Tien Nguyen and Shafiq Joty and Muhammad Imran and Hassan Sajjad and Prasenjit Mitra},
  booktitle={Proceedings of the 4th International Workshop on Social Web for Disaster Management (SWDM)},
  location = {Indianapolis, US},
  month={October},
  year={2016},
}

@inproceedings{eldesouki2016qcri,
  title={{QCRI @ DSL 2016: Spoken Arabic Dialect Identification Using Textual}},
  author={Eldesouki, Mohamed and Dalvi, Fahim and Sajjad, Hassan and Darwish, Kareem},
  booktitle={Proceedings of the 3rd Workshop on NLP for Similar Languages, Varieties and Dialects},
  year={2016},
  month={December},
  location = {Osaka, Japan},
}

@InProceedings{durrani-etal:iwslt16,
author = {Nadir Durrani and Fahim Dalvi and Hassan Sajjad and Stephan Vogel},
title = {{QCRI’s Machine Translation Systems for IWSLT’2016}},
booktitle = {Proceedings of the 13th International Workshop on Spoken Language Translation (IWSLT)},
month = {December},
year = {2016},
location = {Seattle, USA}
}


@InProceedings{guzman-sajjad-etal:iwslt13,
author = {Guzm{\'a}n, Francisco and Sajjad, Hassan and Vogel, Stephan and Abdelali, Ahmed},
title = {The {AMARA} Corpus: Building Resources for Translating the Web's Educational Content},
booktitle = {Proceedings of the 10th International Workshop on Spoken Language Technology (IWSLT)},
month = {December},
year = {2013},
location = {Heidelberg, Germany}

}


@InProceedings{sajjad-etal:iwslt13,
author = {Hassan Sajjad and Francisco Guzmán and Preslav Nakov and Ahmed Abdelali and Kenton Murray and Fahad Al Obaidli and Stephan Vogel},
title = {{QCRI} at {IWSLT} 2013: Experiments in {Arabic-English and English-Arabic} Spoken Language Translation},
booktitle = {Proceedings of the 10th International Workshop on Spoken Language Technology (IWSLT)},
month = {December},
year = {2013},
location = {Heidelberg, Germany}

}

@InProceedings{neurox-aaai19:demo,
  title={NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks},
  author={Fahim Dalvi and Avery Nortonsmith and D. Anthony Bau and Yonatan Belinkov and Hassan Sajjad and Nadir Durrani and James Glass},
  booktitle={AAAI Conference on Artificial Intelligence (AAAI)},
  year={2019},
  location = {Honolulu, USA},
  month={January},
}
@inproceedings{liepins2017summa,
  title={The SUMMA Platform Prototype},
  author={Liepins, Renars and Germann, Ulrich and Barzdins, Guntis and Birch, Alexandra and Renals, Steve and Weberu, Susanne and van der Kreefti, Peggy and Bourlard, Herv{\'e} and PrietoJ, Jo{\~a}o and Klejch, Ondrej and others},
  booktitle={Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL)},
  year={2017},
  month={April},
}

@inproceedings{dalvi2017qcri,
  title={QCRI Live Speech Translation System},
  author={Dalvi, Fahim and Zhang, Yifan and Khurana, Sameer and Durrani, Nadir and Sajjad, Hassan and Abdelali, Ahmed and Mubarak, Hamdy and Ali, Ahmed and Vogel, Stephan},
  booktitle={In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL)},
  year={2017},
  month={April},
}

@inproceedings{diacritic2019emnlp,
  title={A System for Diacritizing Four Varieties of {Arabic}},
  author={Hamdy Mubarak and Ahmed Abdelali and Kareem Darwish and Mohamed Eldesouki and Younes Samih and Hassan Sajjad},
  booktitle={In Proceedings of the Empirical Methods in Natural Language Processing (EMNLP)},
  year={2019},
  month={November},
}

@article{rafae2018:CL,
  title={A Clustering Framework for Lexical Normalization of Roman {Urdu}},
  author={Rafae, Abdul and Karim, Asim and Sajjad, Hassan and Kamiran, Faisal and Jia Xu},
  Journal={Natural Language Engineering (NLE)},
  year = {2020},
 keywords = {journal},
}

@article{madgy2015:SNAM,
 journal = {Social Network Analysis and Mining},
 title = {Bridging social media via distant supervision},
 author = {Magdy, Walid and Sajjad, Hassan and El-Ganainy, Tarek and Sebastiani, Fabrizio},
 year = {2015},
 volume = {35},
 number = {5},
}

@article{joty2017:csl,
 journal = {Computer Speech and Language},
 title = {Domain Adaptation using Neural Network Joint Model},
 author = {Shafiq Joty and Nadir Durrani and Hassan Sajjad and Ahmed Abdelali},
 year = {2017},
 issn = {0885-2308},
 volume = {45},
 number = {C},
 issue_date = {September 2017},
 publisher = {Academic Press Ltd.},
 address = {London, UK, UK},
}

@article{sajjad2017statistical,
  title={Statistical models for unsupervised, semi-supervised and supervised transliteration mining},
  author={Sajjad, Hassan and Schmid, Helmut and Fraser, Alexander and Sch{\"u}tze, Hinrich},
  journal={Computational Linguistics},
  year={2017},
 volume = {43},
 number = {2},
 issue_date = {June 2017},
  publisher={MIT Press One Rogers Street, Cambridge, MA 02142-1209 USA journals-info@ mit. edu},
}

@article{belinkov2020cl,
  title={On the Linguistic Representational Power of Neural Machine Translation Models},
  author={Yonatan Belinkov* and Nadir Durrani* and Hassan Sajjad and Fahim Dalvi and James Glass},
  journal={Computational Linguistics},
  year={2020},
 volume = {46},
 number = {1},
  publisher={MIT Press One Rogers Street, Cambridge, MA 02142-1209 USA journals-info@ mit. edu},
}

@InProceedings{wu_similarity:acl20,
  title={{Similarity Analysis of Contextual Word Representation Models}},
  author={John M. Wu and Yonatan Belinkov and Hassan Sajjad and  Nadir Durrani and Fahim Dalvi and James Glass},
  booktitle={Proceedings of the Annual Conference of the Association for Computational Linguistics (ACL)},
  Month ={July},
  year={2020},
}
@InProceedings{durrani:2019:NAACL,
  title={{One Size Does Not Fit All: Comparing NMT Representations of Different Granularities}},
  author={Nadir Durrani and Fahim Dalvi and Hassan Sajjad and Yonatan Belinkov and Preslav Nakov},
  booktitle={Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)},
  year={2019},
    Month = {June},
    location = {Minneapolis, US},
}
@InProceedings{mubarak:2019:NAACL,
  title={{Highly Effective Arabic Diacritization using Sequence to Sequence Modeling}},
  author={Hamdy Mubarak and Ahmed Abdelali and Hassan Sajjad and Younes Samih and Kareem Darwish},
  booktitle={Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)},
  year={2019},
    Month = {June},
}

@InProceedings{individual:iclr19,
  title={Identifying and Controlling Important Neurons in Neural Machine Translation},
  author={D. Anthony Bau* and Yonatan Belinkov* and Hassan Sajjad and Fahim Dalvi and Nadir Durrani and James Glass},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2019},
 keywords = {conference},
 Month = {May},
 location = {New Orleans, US},
}
@InProceedings{grain:aaai19-1,
  title={What is one Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models},
  author={Fahim Dalvi* and Nadir Durrani* and Hassan Sajjad* and Yonatan Belinkov  and D. Anthony Bau and James Glass},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
  year={2019},
 keywords = {conference},
     Month = {March},
    location = {Honolulu, US},

}

@InProceedings{dalvi:2018:NAACL,
  title={Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation},
  author={Dalvi, Fahim and Durrani, Nadir and Sajjad, Hassan and Vogel, Stephan},
  booktitle={Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)},
  year={2018},
    Month = {June},
    location = {New Orleans, US},
}
@InProceedings{belinkov:2017:ACL,
  title={What do Neural Machine Translation Models Learn about Morphology?},
  author={Belinkov, Yonatan and Durrani, Nadir and Dalvi, Fahim and Sajjad, Hassan and Glass, James},
  booktitle={Proceedings of the 55th Conference of the Association for Computational Linguistics (ACL)},
  year={2017},
    Month = {August},
    location = {Vancouver, Canada},
}
@inproceedings{dalvi:ijcnlp2017,
author = {Fahim Dalvi and Nadir Durrani and Hassan Sajjad and Yonatan Belinkov and Stephan Vogel},
title = {Understanding and Improving Morphological Learning in the Neural Machine Translation Decoder},
booktitle = {Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP)},
year = 2017,
month = {November},
location = {Taipei, Taiwan},
}

@inproceedings{belinkov:ijcnlp2017,
author = {Yonatan Belinkov and Llu\'{i}s M\`arquez and  Hassan Sajjad and Nadir Durrani and Fahim Dalvi and James Glass},
title = {Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks},
booktitle = {Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP)},
year = 2017,
month = {November},
location = {Taipei, Taiwan},
}


@inproceedings{sajjad-EtAl:2011:IJCNLP-2011,
author = {Sajjad, Hassan and Durrani, Nadir and Schmid, Helmut and Fraser, Alexander},
title = {Comparing Two Techniques for Learning Transliteration Models Using a Parallel Corpus},
booktitle = {Proceedings of 5th International Joint Conference on Natural Language Processing (IJCNLP)},
month = {November},
year = {2011},
location = {Chiang Mai, Thailand},
}

@inproceedings{sajjad2013translating,
  title={{Translating Dialectal Arabic to English}},
  author={Sajjad, Hassan and Darwish, Kareem and Belinkov, Yonatan},
  booktitle={Proceedings of the 51st Conference of the Association for Computational Linguistics (ACL)},
  year={2013},
  month = {August},
location = {Sofia, Bulgaria},
}

@InProceedings{uddin:socialcom2014,
author = {Moeen Uddin, Mohammad and Imran, Mohammad and Sajjad, Hassan},
title = {Understanding Types of Users on {T}witter},
booktitle = {Proceedings of the 6th ASE International Conference in Social Computing (SocialCom)},
month = {May},
year = {2014},
location = {Stanford, USA},
}

@inproceedings{darwish2014verifiably,
  title={Verifiably Effective Arabic Dialect Identification.},
  author={Darwish, Kareem and Sajjad, Hassan and Mubarak, Hamdy},
  booktitle={Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2014},
    month={October},
  location={Doha, Qatar},
}

@inproceedings{rafae2015unsupervised,
  title={An Unsupervised Method for Discovering Lexical Variations in Roman {Urdu} Informal Text.},
  author={Rafae, Abdul and Qayyum, Abdul and Uddin, Muhammad Moeen and Karim, Asim and Sajjad, Hassan and Kamiran, Faisal},
  booktitle={Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  location ={Lisbon, Portugal},
  year={2015},
  month={September},
}


@InProceedings{nguyen:icwsm2017,
  title={Robust Classification of Crisis-Related Data on Social Networks using Convolutional Neural Networks},
  author={Dat Tien Nguyen and Kamla Al-Mannai and Shafiq Joty and Hassan Sajjad and Muhammad Imran and Prasenjit Mitra},
  booktitle={Proceedings of the 11th International AAAI Conference on Web and Social Media (ICWSM)},
  location = {Montreal, Canada},
  month={May},
  year={2017},
}

@InProceedings{sajjad-etal:2017:ACLShort,
  author    = {Hassan Sajjad and Fahim Dalvi and Nadir Durrani and Ahmed Abdelali and Yonatan Belinkov and Stephan Vogel},
  title     = {{Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging}},
  booktitle = {Proceedings of the 55th Conference of the Association for Computational Linguistics (ACL)},
  year      = {2017},
    Month = {August},
  location = {Vancouver, Canada},
}

@InProceedings{durrani-EtAl:2016:COLING,
  author    = {Durrani, Nadir  and  Sajjad, Hassan  and  Joty, Shafiq  and  Abdelali, Ahmed},
  title     = {A Deep Fusion Model for Domain Adaptation in Phrase-based MT},
  booktitle = {Proceedings of the 26th International Conference on Computational Linguistics (COLING)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
}

@inproceedings{sajjad2016eyes,
  title={Eyes Don't Lie: Predicting Machine Translation Quality Using Eye Movement.},
  author={Sajjad, Hassan and Guzm{\'a}n, Francisco and Durrani, Nadir and Abdelali, Ahmed and Bouamor, Houda and Temnikova, Irina P and Vogel, Stephan},
  booktitle={Proceedings of the 15th Annual Conference of the North American Chapter of the
Association of Computational Linguistics: Human Language Technologies (NAACL-HLT)},
  year={2016},
  location = {San Diego, US},
  month = {June},
}

@InProceedings{sajjad16:postediting,
  title={An Empirical Study: Post-editing Effort for English to Arabic Hybrid Machine Translation},
  author={Sajjad, Hassan and Guzm{\'a}n, Francisco and Vogel, Stephan},
  booktitle={Proceedings of the Association for Machine Translation in the Americas (AMTA)},
  location = {Austin, US},
  month={October},
  year={2016},
}


@InProceedings{durrani-EtAl:2014:EACL,
  author    = {Durrani, Nadir  and  Sajjad, Hassan  and  Hoang,  Hieu  and  Koehn, Philipp},
  title     = "{Integrating an Unsupervised Transliteration Model into Statistical Machine Translation}",
booktitle = {Proceedings of the 15th Conference of the European Chapter of the ACL (EACL)},
  month     = {April},
  year      = {2014},
  address   = {Gothenburg, Sweden},
}

@InProceedings{Abdelali_2014_lrec,
author = {Ahmed Abdelali and Francisco Guzman and Hassan Sajjad and Stephan Vogel},
title = {The {AMARA} Corpus: Building Parallel Language Resources for the Educational Domain},
booktitle = {Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC)},
year = {2014},
month = {May},
address = {Reykjavik, Iceland},
}

@inproceedings{durraniEtAl:MT-Summit2015,
  address = {Florida, USA},
  author = {Durrani, Nadir and Sajjad, Hassan and Joty, Shafiq, and Abdelali, Ahmed and Vogel, Stephan},
  booktitle = {Proceedings of the 15th Machine Translation Summit (MT Summit XV)},
  title = {Using Joint Models for Domain Adaptation in Statistical Machine Translation},
  Month = {November},
  year = {2015},
}

@inproceedings{magdy2015distant,
  title={Distant Supervision for Tweet Classification Using YouTube Labels},
  author={Magdy, Walid and Sajjad, Hassan and El-Ganainy, Tarek and Sebastiani, Fabrizio},
  booktitle={Proceedings of the Ninth International AAAI Conference on Web and Social Media (ICWSM)},
  location={Oxford, UK},
  month ={May},
  year={2015},
}

@InProceedings{joty-etAL:2015:EMNLP,
  author    = {Joty, Shafiq  and  Sajjad, Hassan and Durrani, Nadir and Al-Mannai, Kamla and Abdelali, Ahmed and Vogel, Stephan},
  title     = "{How to Avoid Unwanted Pregnancies: Domain Adaptation using Neural Network Models}",
  booktitle = {Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  month     = {September},
  year      = {2015},
  address   = {Lisbon, Portugal},

}
@article{SOLID,
    title={A large-scale semi-supervised dataset for offensive language identification},
    author={Sara Rosenthal and Pepa Atanasova and Georgi Karadzhov and Marcos Zampieri and Preslav Nakov},
    year={2020},
    journal={ArXiv preprint 2004.14454},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

@article{alam2020call2arms,
    title={Fighting the {COVID}-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms},
    author={Firoj Alam and Fahim Dalvi and Shaden Shaar and Nadir Durrani and Hamdy Mubarak and Alex Nikolov and Giovanni Da San Martino and Ahmed Abdelali and Hassan Sajjad and Kareem Darwish and Preslav Nakov},
    year={2020},
    journal={ArXiv preprint 2007.07996},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

@article{alam2020fighting,
    title={Fighting the {COVID}-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society},
    author={Firoj Alam and Shaden Shaar and Fahim Dalvi and Hassan Sajjad and Alex Nikolov and Hamdy Mubarak and Giovanni Da San Martino and Ahmed Abdelali and Nadir Durrani and Kareem Darwish and Preslav Nakov},
    year={2020},
    journal={ArXiv preprint 2005.00033},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

@InProceedings{CIKM2020:FANG,
  author =  "Van-Hoang Nguyen and Kazunari Sugiyama and Preslav Nakov and Min-Yen Kan",
  title =   "{FANG}: Leveraging Social Context for Fake News Detection Using Graph Representation",
  booktitle =   "Proceedings of the 29th ACM International Conference on Information and Knowledge Management",
  series = {CIKM~'20},
  year =  "2020",
}

@InProceedings{clef-checkthat:2020,
 author = "Barr\'{o}n-Cede{\~n}o, Alberto and
    Elsayed, Tamer and
    Nakov, Preslav and
    {Da San Martino}, Giovanni and
    Hasanain, Maram and
    Suwaileh, Reem and
    Haouari, Fatima and
    Babulkov, Nikolay and
    Hamdan, Bayan and
    Nikolov, Alex and
    Shaar, Shaden and
    Ali, {Zien Sheikh}",
 title  = "{Overview of CheckThat! 2020} --- Automatic Identification and
Verification of Claims in Social Media",
 year = {2020},
 booktitle = "Proceedings of the 11th International Conference of the CLEF Association: Experimental IR Meets Multilinguality, Multimodality, and Interaction",
 series = {CLEF~'2020},
 address = {Thessaloniki, Greece},
 nopages="--",
}


@InProceedings{clef-checkthat-ar:2020,
 author = "Hasanain, Maram and
    Haouari, Fatima and
    Suwaileh, Reem and
    Ali, {Zien Sheikh} and
    Hamdan, Bayan and
    Elsayed, Tamer and
    Barr\'{o}n-Cede{\~n}o, Alberto and
    {Da San Martino}, Giovanni and
    Nakov, Preslav",
 title = "Overview of {CheckThat!} 2020 {A}rabic: Automatic Identification and Verification of Claims in Social Media",
 booktitle = "Working Notes of CLEF 2020---Conference and Labs of the Evaluation Forum",
 series = {CLEF~'2020},
 address = {Thessaloniki, Greece},
 year = {2020}
}


@InProceedings{clef-checkthat-en:2020,
 author = "Shaar, Shaden and
    Nikolov, Alex and
    Babulkov, Nikolay and
    Alam, Firoj and
    Barr\'{o}n-Cede{\~n}o, Alberto and
    Elsayed, Tamer and
    Hasanain, Maram and
    Suwaileh, Reem and
    Haouari, Fatima and
    {Da San Martino}, Giovanni and
    Nakov, Preslav",
 title = "Overview of {CheckThat!} 2020 {E}nglish: Automatic Identification and Verification of Claims in Social Media",
  booktitle = "Working Notes of CLEF 2020---Conference and Labs of the Evaluation Forum",
  series = {CLEF~'2020},
  address = {Thessaloniki, Greece},
  year = {2020}
}

@inproceedings{stefanov-etal-2020-predicting,
    title = "Predicting the Topical Stance and Political Leaning of Media using Tweets",
    author = "Stefanov, Peter  and
      Darwish, Kareem  and
      Atanasov, Atanas  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    series = {ACL~'20},
    month={July},
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-main.50",
    pages = "527--537",
}

@inproceedings{baly-etal-2020-written,
    title = "What Was Written vs. Who Read It: News Media Profiling Using Text Analysis and Social Media Context",
    author = "Baly, Ramy  and
      Karadzhov, Georgi  and
      An, Jisun  and
      Kwak, Haewoon  and
      Dinkov, Yoan  and
      Ali, Ahmed  and
      Glass, James  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    series = {ACL~'20},
    month={July},
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-main.308",
    pages = "3364--3374",
}

@inproceedings{shaar-etal-2020-known,
    title = "That is a Known Lie: Detecting Previously Fact-Checked Claims",
    author = "Shaar, Shaden  and
      Babulkov, Nikolay  and
      Da San Martino, Giovanni  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    series = {ACL~'20},
    month={July},
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-main.332",
    pages = "3607--3618",
}

@inproceedings{da-san-martino-etal-2020-prta,
    title = "{P}rta: A System to Support the Analysis of Propaganda Techniques in the News",
    author = "Da San Martino, Giovanni  and
      Shaar, Shaden  and
      Zhang, Yifan  and
      Yu, Seunghak  and
      Barr{\'o}n-Cede{\~n}o, Alberto  and
      Nakov, Preslav",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
    series = {ACL~'20},
    month={July},
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.acl-demos.32",
    pages = "287--293",
}

@InProceedings{IJCAI2020:propaganda:survey,
  author    = {Da San Martino, Giovanni and Stefano Cresci and Barr\'{o}n-Cede\~no, Alberto and Seunghak Yu and Di Pietro, Roberto and Preslav Nakov},
  title     = {A Survey on Computational Propaganda Detection},
  booktitle = {Proceedings of the 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence},
  series    = {IJCAI-PRICAI~'20},
  year      = {2020},
  address   = {Yokohama, Japan},
}


@inproceedings{zampieri-etal-2020-semeval,
    title = {{SemEval-2020} Task 12: Multilingual Offensive Language Identification in Social Media},
    author = {Zampieri, Marcos and Nakov, Preslav and Rosenthal, Sara and Atanasova, Pepa and Karadzhov, Georgi and Mubarak, Hamdy and Derczynski, Leon and Pitenis, Zeses and {\c C} {\" o}ltekin, {\c C}a{\u g}r{\i}},
    booktitle = {Proceedings of the International Workshop on Semantic Evaluation},
    series = {SemEval~'20},
    address = {Barcelona, Spain},
    year = {2020},
    month = {December},
}

@InProceedings{DaSanMartinoSemeval20task11,
  author = {Da San Martino, Giovanni and
  Barr\'{o}n-Cede\~no, Alberto and
  Wachsmuth, Henning and
  Petrov, Rostislav and
  Nakov, Preslav},
  title = {{SemEval}-2020 Task 11: Detection of Propaganda Techniques in News Articles},
  booktitle = {Proceedings of the International Workshop on Semantic Evaluation},
  series = {SemEval~'20},
  year = {2020},
  address = {Barcelona, Spain},
  month = {December},
}

@InProceedings{CheckThat:ECIR2020,
  author    = {Alberto Barr{\'{o}}n{-}Cede{\~{n}}o and
               Tamer Elsayed and
               Preslav Nakov and
               Giovanni Da San Martino and
               Maram Hasanain and
               Reem Suwaileh and
               Fatima Haouari},
  title     = {CheckThat! at {CLEF} 2020: Enabling the Automatic Identification and Verification of Claims in Social Media},
    booktitle = {Proceedings of the 42nd European Conference on Information Retrieval},
    series = {ECIR~'19},
    pages = {499--507},
    address   = {Lisbon, Portugal},
    month     = {April},
    year      = {2020},
}

@InProceedings{ICWSM2020:Unsupervised:Stance:Twitter,
  author =  "Kareem Darwish and Michael Aupetit and Peter Stefanov and Preslav Nakov",
  title =   "Unsupervised User Stance Detection on Twitter",
  booktitle =   "Proceedings of the International AAAI Conference on Web and Social Media",
  series = {ICWSM~'20},
  year =  "2020",
  pages = {141--152},
  address =  "Atlanta, GA, USA",
}

@InProceedings{ASRU2019:deception,
  author =  "Daniel Kopev and Ahmed Ali and Ivan Koychev and Preslav Nakov",
  title =   "Detecting Deception in Political Debates Using Acoustic and Textual Features",
  booktitle =   "Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop",
  series = {ASRU~'19},
  month = {December},
  year =  "2019",
  pages = {652--659},
  address =  "Singapore",
}

@InProceedings{NeurIPS2019:propaganda,
  author =  "Yu, Seunghak and Da San Martino, Giovanni and Nakov, Preslav",
  title =   "Experiments in Detecting Persuasion Techniques in the News",
  booktitle =   "Proceedings of the NeurIPS 2019 Joint Workshop on AI for Social Good",
  series = {NeurIPS~'19},
  month = {December},
  year =  "2019",
  address =  "Vancouver, Canada",
}

@InProceedings{NLP4IF2019:propaganda:task,
  author =  "Da San Martino, Giovanni and Alberto Barron-Cedeno and Preslav Nakov",
  title =   "Findings of the {NLP4IF}-2019 Shared Task on Fine-Grained Propaganda Detection",
  booktitle =   "Proceedings of the 2nd Workshop on NLP for Internet Freedom (NLP4IF): Censorship, Disinformation, and Propaganda",
  series = {NLP4IF\@EMNLP~'19},
  NOmonth = {November},
  year =  "2019",
  pages = "162--170",
  address =  "Hong Kong, China",
}

@InProceedings{CoNLL2019:troll:roles,
  author =  "Atanas Atanasov and De Francisci Morales, Gianmarco and Preslav Nakov",
  title =   "Predicting the Role of Political Trolls in Social Media",
  booktitle =   "Proceedings of the 2019 SIGNLL Conference on Computational Natural Language Learning",
  month = {November},
  series = {CoNLL~'19},
  pages = "1023--1034",
  year =  "2019",
  address =  "Hong Kong, China",
}

@InProceedings{EMNLP2019:Stance:crosslanguage:contrastive,
  author =  "Mitra Mohtarami and James Glass and Preslav Nakov",
  title =   "Contrastive Language Adaptation for Cross-Lingual Stance Detection",
  booktitle =   "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
  month = {November},
  pages = {4442--4452},
  series = {EMNLP~'19},
  year =  "2019",
  address =  "Hong Kong, China",
}

@InProceedings{EMNLP2019:propaganda:finegrained,
  author =  "Da San Martino, Giovanni and Seunghak Yu and Alberto Barron-Cedeno and Rostislav Petrov and Preslav Nakov",
  title =   "Fine-Grained Analysis of Propaganda in News Articles",
  booktitle =   "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
  month = {November},
  series = {EMNLP~'19},
  year =  "2019",
  pages = "5636--5646",
  address =  "Hong Kong, China",
}

@InProceedings{EMNLP2019:fauxtography,
  author =  "Dimitrina Zlatkova and Preslav Nakov and Ivan Koychev",
  title =   "Fact-Checking Meets Fauxtography: Verifying Claims About Images",
  booktitle =   "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
  month = {November},
  series = {EMNLP~'19},
  pages = "2099--2108",
  year =  "2019",
  address =  "Hong Kong, China",
}

@InProceedings{EMNLP2019:tanbih,
  author =  "Yifan Zhang and Giovanni Da San Martino and Alberto Barrón-Cedeño and Salvatore Romeo and Jisun An and Haewoon Kwak and Todor Staykovski and Israa Jaradat and Georgi Karadzhov and Ramy Baly and Kareem Darwish and James Glass, Preslav Nakov",
  title =   "Tanbih: Get To Know What You Are Reading",
  booktitle =   "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
  month = {November},
  series = {EMNLP~'19},
  year =  "2019",
  pages = "223--228",
  address =  "Hong Kong, China",
}

@inproceedings{INTERSPEECH2019:youtube,
  title={Predicting the Leading Political Ideology of {Y}outube Channels Using Acoustic, Textual and Metadata Information},
  author={Yoan Dinkov and Ahmed Ali and Ivan Koychev and Preslav Nakov},
  booktitle={Proceedings of the 20th Annual Conference of the International Speech Communication Association},
  series = {INTERSPEECH~'19},
  address = {Graz, Austria},
  month = {September},
  pages = {501--505},
  year={2019},
}

@inproceedings{RANLP2019:toxicity,
  title={Detecting Toxicity in News Articles: Application to {B}ulgarian},
  author={Yoan Dinkov and Ivan Koychev and Preslav Nakov},
  booktitle={Proceedings of the International Conference on Recent Advances in Natural Language Processing},
  month = {September},
  series = {RANLP~'19},
  address = {Varna, Bulgaria},
  pages = "247--258",
  year={2019},
}

@inproceedings{RANLP2019:checkworthiness:multitask,
  title={It Takes Nine to Smell a Rat: Neural Multi-Task Learning for Check-Worthiness Prediction},
  author={Slavena Vasileva and Pepa Atanasova and Lluís Màrquez and Alberto Barrón-Cedeño and Preslav Nakov},
  booktitle={Proceedings of the International Conference on Recent Advances in Natural Language Processing},
  month = {September},
  series = {RANLP~'19},
  address = {Varna, Bulgaria},
  year={2019},
  pages = "1229--1239",
}


@InProceedings{clef-checkthat:2019,
 author = "Elsayed, Tamer and
    Nakov, Preslav and
    Barr\'{o}n-Cede{\~n}o, Alberto and
    Hasanain, Maram and
    Suwaileh, Reem and
    {Da San Martino}, Giovanni and
    Atanasova, Pepa",
 title  = "Overview of the {CLEF-2019 CheckThat!}: Automatic Identification and Verification of Claims",
 booktitle = "Experimental IR Meets Multilinguality, Multimodality, and Interaction",
 series    = "LNCS",
 publisher = "Springer",
 address   = "Lugano, Switzerland",
 month     = "September",
 year      = 2019
}


@InProceedings{CheckThat:ECIR2019,
    author    = {Elsayed, Tamer and Nakov, Preslav  and  Barr\'{o}n-Cede\~{n}o, Alberto and Hasanain, Maram and Suwaileh, Reem and Atanasova, Pepa and Da San Martino, Giovanni},
    title     = {{CheckThat}! at {CLEF} 2019: Automatic Identification and Verification of Claims},
    booktitle = {Proceedings of the 41st European Conference on Information Retrieval (ECIR'19)},
    series = {ECIR~'19},
    pages = {309--315},
    address   = {Cologne, Germany},
    month     = {April},
    year      = {2019},
}


@InProceedings{OffenseEval:NAACL:2019,
  author =  "Marcos Zampieri and Shervin Malmasi and Preslav Nakov and Sara Rosenthal and Noura Farra and Ritesh Kumar",
  title =   "Predicting the Type and Target of Offensive Posts in Social Media",
  booktitle = {Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  series    = {NAACL-HLT~'19},
  year =  "2019",
  pages = {1415--1420},
  NOpublisher =   "Association for Computational Linguistics",
  address =  "Minneapolis, MN, USA",
  NOurl = {https://www.aclweb.org/anthology/N19-1144.pdf}
}


@article{Barron:19,
  author = "Barr\'{o}n-Cede\~no, Alberto and
    Da San Martino, Giovanni and
    Jaradat, Israa and
    Nakov, Preslav",
  title = "{Proppy: Organizing the news based on their propagandistic content}",
  journal = "Information Processing \& Management",
  volume = "56",
  number = "5",
  pages = "1849 - 1864",
  year = "2019",
  issn = "0306-4573",
  NOdoi = "https://doi.org/10.1016/j.ipm.2019.03.005",
  NOurl = "http://www.sciencedirect.com/science/article/pii/S0306457318306058",
}

@InProceedings{AAAI2019:proppy,
author = {Alberto Barr\'on-Cede{\~n}o and Da San Martino, Giovanni and Jaradat, Israa and Nakov, Preslav},
title = {Proppy: A System to Unmask Propaganda in Online News},
booktitle = {Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence},
series = {AAAI'19},
year = {2019},
pages = {9847--9848},
address = {Honolulu, HI, USA},
NOmonth = {January},
}

@InProceedings{source:multitask:NAACL:2019,
  author =  "Ramy Baly and Georgi Karadzhov and Abdelrhman Saleh and James Glass and Preslav Nakov",
  title =   "Multi-Task Ordinal Regression for Jointly Predicting the Trustworthiness and the Leading Political Ideology of News Media",
  booktitle = {Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  series    = {NAACL-HLT~'19},
  year =  "2019",
  pages = "2109--2116",
  NOpublisher =   "Association for Computational Linguistics",
  address =  "Minneapolis, MN, USA",
  NOurl = "https://www.aclweb.org/anthology/N19-1216.pdf"
}

@article{Atanasova:2019:AFU:3331015.3297722,
 author = {Atanasova, Pepa and Nakov, Preslav and M\`{a}rquez, Llu\'{\i}s and Barr\'{o}n-Cede\~{n}o, Alberto and Karadzhov, Georgi and Mihaylova, Tsvetomila and Mohtarami, Mitra and Glass, James},
 title = {Automatic Fact-Checking Using Context and Discourse Information},
 journal = {J. Data and Information Quality},
 issue_date = {June 2019},
 volume = {11},
 number = {3},
 month = {May},
 year = {2019},
 issn = {1936-1955},
 pages = {12:1--12:27},
 articleno = {12},
 numpages = {27},
 NOurl = {http://doi.acm.org/10.1145/3297722},
 NOdoi = {10.1145/3297722},
 acmid = {3297722},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Fact-checking, community question-answering, discourse},
}

@InProceedings{D18-1389,
  author =  "Baly, Ramy
    and Karadzhov, Georgi
    and Alexandrov, Dimitar
    and Glass, James
    and Nakov, Preslav",
  title =   "Predicting Factuality of Reporting and Bias of News Media Sources",
  booktitle =   "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
  series = {EMNLP~'18},
  year =  "2018",
  NOpublisher =   "Association for Computational Linguistics",
  pages =   "3528--3539",
  address =  "Brussels, Belgium",
  NOurl =   "http://aclweb.org/anthology/D18-1389"
}

@InProceedings{NAACL2018:stance,
  author    = {Mitra Mohtarami and Ramy Baly and James Glass and Preslav Nakov and Llu\'{i}s M\`{a}rquez and Alessandro Moschitti},
  title     = {Automatic Stance Detection Using End-to-End Memory Networks},
  booktitle = {Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  series    = {NAACL-HLT~'18},
  year      = {2018},
  address   = {New Orleans, Louisiana, USA},
  pages = {767--776},
  NOmonth     = {June},
  noURL     = "http://aclweb.org/anthology/N18-1070"
}


@InProceedings{clef2018checkthat:overall,
    author    = {Nakov, Preslav  and  Barr\'{o}n-Cede\~{n}o, Alberto and Elsayed, Tamer and Suwaileh, Reem and M\`{a}rquez, Llu\'{i}s and Zaghouani, Wajdi and Atanasova, Pepa and Kyuchukov, Spas and Da San Martino, Giovanni},
    title     = {Overview of the {CLEF-2018 CheckThat! Lab} on Automatic Identification and Verification of Political Claims},
    booktitle = {Proceedings of the Ninth International Conference of the CLEF Association: Experimental IR Meets Multilinguality, Multimodality, and Interaction},
    series    = {Lecture Notes in Computer Science},
    publisher = {Springer},
    address   = {Avignon, France},
    NOmonth     = {September},
    year      = {2018},
    pages = {372--387}
}

@InProceedings{clef2018checkthat:task1,
    author    = {Atanasova, Pepa and  M\`{a}rquez, Llu\'{i}s  and Barr\'{o}n-Cede\~{n}o, Alberto  and Elsayed, Tamer and Suwaileh, Reem and Zaghouani, Wajdi and Kyuchukov, Spas and Da San Martino, Giovanni and Nakov, Preslav},
    title     = {Overview of the {CLEF-2018 CheckThat! Lab} on Automatic Identification and Verification of Political Claims, {T}ask 1: Check-Worthiness},
    booktitle = {CLEF 2018 Working Notes. Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum},
    series    = {{CEUR} Workshop Proceedings},
    publisher = {CEUR-WS.org},
    editor    = {Cappellato, Linda and Ferro, Nicola and Nie, Jian-Yun and Soulier, Laure},
    address   = {Avignon, France},
    NOmonth     = {September},
    year      = {2018},
}


@InProceedings{clef2018checkthat:task2,
    author    = {Barr\'{o}n-Cede\~{n}o, Alberto and Elsayed, Tamer and Suwaileh, Reem and M\`{a}rquez, Llu\'{i}s  and Atanasova, Pepa and Zaghouani, Wajdi and Kyuchukov, Spas and Da San Martino, Giovanni and Nakov, Preslav},
    title     = {Overview of the {CLEF-2018 CheckThat! Lab} on Automatic Identification and Verification of Political Claims, {T}ask 2: Factuality},
    booktitle = {CLEF 2018 Working Notes. Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum},
    series    = {{CEUR} Workshop Proceedings},
    publisher = {CEUR-WS.org},
    editor    = {Cappellato, Linda and Ferro, Nicola and Nie, Jian-Yun and Soulier, Laure},
    address   = {Avignon, France},
    NOmonth     = {September},
    year      = {2018},
}

@inproceedings{mubarak2020spam,
  title={Spam Detection on Arabic Twitter},
  author={Mubarak, Hamdy and Abdelali, Ahmed and Hassan, Sabit and Darwish, Kareem},
  booktitle={International Conference on Social Informatics},
  pages={237--251},
  year={2020},
  organization={Springer}
}

@article{zampieri2020semeval,
  title={SemEval-2020 task 12: Multilingual offensive language identification in social media (OffensEval 2020)},
  author={Zampieri, Marcos and Nakov, Preslav and Rosenthal, Sara and Atanasova, Pepa and Karadzhov, Georgi and Mubarak, Hamdy and Derczynski, Leon and Pitenis, Zeses and {\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
  journal={arXiv preprint arXiv:2006.07235},
  year={2020}
}

@inproceedings{shon2020adi17,
  title={ADI17: A Fine-Grained Arabic Dialect Identification Dataset},
  author={Shon, Suwon and Ali, Ahmed and Samih, Younes and Mubarak, Hamdy and Glass, James},
  booktitle={ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={8244--8248},
  year={2020},
  organization={IEEE}
}

@inproceedings{mubarak-etal-2020-constructing,
    title = "Constructing a Bilingual Corpus of Parallel Tweets",
    author = "Mubarak, Hamdy  and
      Hassan, Sabit  and
      Abdelali, Ahmed",
    booktitle = "Proceedings of the 13th Workshop on Building and Using Comparable Corpora",
    month = {may},
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://www.aclweb.org/anthology/2020.bucc-1.3",
    pages = "14--21",
    abstract = "In a bid to reach a larger and more diverse audience, Twitter users often post parallel tweets{---}tweets that contain the same content but are written in different languages. Parallel tweets can be an important resource for developing machine translation (MT) systems among other natural language processing (NLP) tasks. In this paper, we introduce a generic method for collecting parallel tweets. Using this method, we collect a bilingual corpus of English-Arabic parallel tweets and a list of Twitter accounts who post English-Arabictweets regularly. Since our method is generic, it can also be used for collecting parallel tweets that cover less-resourced languages such as Serbian and Urdu. Additionally, we annotate a subset of Twitter accounts with their countries of origin and topic of interest, which provides insights about the population who post parallel tweets. This latter information can also be useful for author profiling tasks.",
    language = "English",
    ISBN = "979-10-95546-42-9",
}

@inproceedings{hassan-etal-2020-alt-semeval,
    title = "{ALT} at {S}em{E}val-2020 Task 12: {A}rabic and {E}nglish Offensive Language Identification in Social Media",
    author = "Hassan, Sabit  and
      Samih, Younes  and
      Mubarak, Hamdy  and
      Abdelali, Ahmed",
    booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
    month = "dec",
    year = "2020",
    address = "Barcelona (online)",
    publisher = "International Committee for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.semeval-1.249",
    pages = "1891--1897",
    abstract = "This paper describes the systems submitted by the Arabic Language Technology group (ALT) at SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media. We focus on sub-task A (Offensive Language Identification) for two languages: Arabic and English. Our efforts for both languages achieved more than 90{\%} macro-averaged F1-score on the official test set. For Arabic, the best results were obtained by a system combination of Support Vector Machine, Deep Neural Network, and fine-tuned Bidirectional Encoder Representations from Transformers (BERT). For English, the best results were obtained by fine-tuning BERT.",
}

@inproceedings{hassan2020alt,
  title={ALT submission for OSACT shared task on offensive language detection},
  author={Hassan, Sabit and Samih, Younes and Mubarak, Hamdy and Abdelali, Ahmed and Rashed, Ammar and Chowdhury, Shammur Absar},
  booktitle={Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection},
  pages={61--65},
  year={2020}
}

@inproceedings{chowdhury2020multi,
  title={A Multi-Platform Arabic News Comment Dataset for Offensive Language Detection},
  author={Chowdhury, Shammur Absar and Mubarak, Hamdy and Abdelali, Ahmed and Jung, Soon-gyo and Jansen, Bernard J and Salminen, Joni},
  booktitle={Proceedings of The 12th Language Resources and Evaluation Conference},
  pages={6203--6212},
  year={2020}
}

@inproceedings{ali2019mgb,
  title={The mgb-5 challenge: Recognition and dialect identification of dialectal arabic speech},
  author={Ali, Ahmed and Shon, Suwon and Samih, Younes and Mubarak, Hamdy and Abdelali, Ahmed and Glass, James and Renals, Steve and Choukri, Khalid},
  booktitle={2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)},
  pages={1026--1033},
  year={2019},
  organization={IEEE}
}

@article{nakov2019arabic,
  title={Arabic community question answering},
  author={Nakov, Preslav and M{\`a}rquez, Llu{\'\i}s and Moschitti, Alessandro and Mubarak, Hamdy},
  journal={Natural Language Engineering},
  volume={25},
  number={1},
  pages={5--41},
  year={2019},
  publisher={Cambridge University Press}
}

@article{elmadany2018arsas,
  title={Arsas: An arabic speech-act and sentiment corpus of tweets},
  author={Elmadany, AbdelRahim and Mubarak, Hamdy and Magdy, Walid},
  journal={OSACT},
  volume={3},
  pages={20},
  year={2018}
}

@inproceedings{alharbi2018part,
  title={Part-of-speech tagging for Arabic Gulf dialect using Bi-LSTM},
  author={Alharbi, Randah and Magdy, Walid and Darwish, Kareem and Abdelali, Ahmed and Mubarak, Hamdy},
  booktitle={Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
  year={2018}
}

@inproceedings{mubarak2018build,
  title={Build Fast and Accurate Lemmatization for Arabic},
  author={Mubarak, Hamdy},
  booktitle={Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
  year={2018}
}

@inproceedings{freihat2018single,
  title={A single-model approach for Arabic segmentation, POS tagging, and named entity recognition},
  author={Freihat, Abed Alhakim and Bella, Gabor and Mubarak, Hamdy and Giunchiglia, Fausto},
  booktitle={2018 2nd International Conference on Natural Language and Speech Processing (ICNLSP)},
  pages={1--8},
  year={2018},
  organization={IEEE}
}

@inproceedings{mubarak2017crowdsourcing,
  title={Crowdsourcing Speech and Language Data for Resource-Poor Languages},
  author={Mubarak, Hamdy},
  booktitle={International Conference on Advanced Intelligent Systems and Informatics},
  pages={440--447},
  year={2017},
  organization={Springer}
}

@inproceedings{ali2016mgb,
  title={The MGB-2 challenge: Arabic multi-dialect broadcast media recognition},
  author={Ali, Ahmed and Bell, Peter and Glass, James and Messaoui, Yacine and Mubarak, Hamdy and Renals, Steve and Zhang, Yifan},
  booktitle={2016 IEEE Spoken Language Technology Workshop (SLT)},
  pages={279--284},
  year={2016},
  organization={IEEE}
}


@inproceedings{wray2015best,
  title={Best practices for crowdsourcing dialectal arabic speech transcription},
  author={Wray, Samantha and Mubarak, Hamdy and Ali, Ahmed},
  booktitle={Proceedings of the Second Workshop on Arabic Natural Language Processing},
  pages={99--107},
  year={2015}
}


@inproceedings{belinkov2015answer,
  title={Answer selection in arabic community question answering: A feature-rich approach},
  author={Belinkov, Yonatan and Barr{\'o}n-Cedeno, Alberto and Mubarak, Hamdy},
  booktitle={Proceedings of the second workshop on arabic natural language processing},
  pages={183--190},
  year={2015}
}

@inproceedings{nicosia2015qcri,
  title={QCRI: Answer selection for community question answering-Experiment for Arabic and English},
  author={Nicosia, Massimo and Filice, Simone and Barr{\'o}n-Cedeno, Alberto and Saleh, Iman and Mubarak, Hamdy and Gao, Wei and Nakov, Preslav and MARTINO, Giovanni Da San and Moschitti, Alessandro and Darwish, Kareem and others},
  year={2015},
  organization={Association for Computational Linguistics}
}

@inproceedings{ali2014advances,
  title={Advances in dialectal arabic speech recognition: A study using twitter to improve egyptian asr},
  author={Ali, Ahmed and Mubarak, Hamdy and Vogel, Stephan},
  booktitle={International Workshop on Spoken Language Translation (IWSLT 2014)},
  year={2014}
}

@inproceedings{mousi-etal-2024-exploring,title = {Exploring Alignment in Shared Cross-lingual Spaces},author = {Mousi, Basel and Durrani, Nadir and Dalvi, Fahim and Hawasly, Majd and Abdelali, Ahmed},editor = {Ku, Lun-Wei and Martins, Andre and Srikumar, Vivek},booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},month = aug,year = {2024},address = {Bangkok, Thailand},publisher = {Association for Computational Linguistics},url = {https://aclanthology.org/2024.acl-long.344},pages = {6326--6348},area = {Latent Concepts}}

@article{chowdhury2024:csl,title = {What do end-to-end speech models learn about speaker, language and channel information? A layer-wise and neuron-level analysis},journal = {Computer Speech and Language},address = {London, UK, UK},volume = {83},pages = {101539},year = {2024},issn = {0885-2308},doi = {https://doi.org/10.1016/j.csl.2023.101539},url = {https://www.sciencedirect.com/science/article/pii/S088523082300058X},author = {Chowdhury, Shammur Absar and Durrani, Nadir and Ali, Ahmed},keywords = {Speech, Neuron-level analysis, Interpretability, Diagnostic classifier, AI explainability, End-to-end architecture},area = {Representation Analysis}}

@article{JMLR:v24:23-0074,author = {Durrani, Nadir and Dalvi, Fahim and Sajjad, Hassan},title = {Discovering Salient Neurons in deep NLP models},journal = {Journal of Machine Learning Research},year = {2023},volume = {24},number = {362},pages = {1--40},area = {Neuron Analysis}}

@inproceedings{fan-et-al-2023-neuron-eval,author = {Fan, Yimin and Dalvi, Fahin and Durrani, Nadir and Sajjad, Hassan},booktitle = {Advances in Neural Information Processing Systems},editor = {Koyejo, S. and Mohamed, S. and Agarwal, A. and Belgrave, D. and Cho, K. and Oh, A.},pages = {1--13},publisher = {Curran Associates, Inc.},title = {Evaluating Neuron Interpretation Methods of NLP Models},volume = {36},year = {2023},area = {Neuron Analysis}}


@inproceedings{mousi-etal-2023-llms,title = {Can {LLM}s Facilitate Interpretation of Pre-trained Language Models?},author = {Mousi, Basel and Durrani, Nadir and Dalvi, Fahim},editor = {Bouamor, Houda and Pino, Juan and Bali, Kalika},booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},month = dec,year = {2023},address = {Singapore},publisher = {Association for Computational Linguistics},url = {https://aclanthology.org/2023.emnlp-main.196},doi = {10.18653/v1/2023.emnlp-main.196},pages = {3248--3268},area = {Large Language Models}}

@article{sajjad2023:csl,address = {London, UK, UK},author = {Sajjad, Hassan and Dalvi, Fahim and Durrani, Nadir and Nakov, Preslav},issn = {0885-2308},doi = {https://doi.org/10.1016/j.csl.2022.101429},url = {https://www.sciencedirect.com/science/article/pii/S0885230822000596},issue_date = {January 2023},journal = {Computer Speech and Language},number = {C},publisher = {Academic Press Ltd.},title = {On the Effect of Dropping Layers of Pre-trained Transformer Models},volume = {77},pages = {101429},year = {2023},area = {Transfer Learning}}

@inproceedings{dalvi-etal-2023-neurox,title = {NeuroX Library for Neuron Analysis of Deep NLP Models},author = {Dalvi, Fahim and Durrani, Nadir and Sajjad, Hassan},booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics: System Demonstrations},month = jul,year = {2023},address = {Toronto, Canada},publisher = {Association for Computational Linguistics},pages = {75--83},area = {Demos and Tools}}

@inproceedings{dalvi-etal-2023-nxplain,title = {{N}x{P}lain: A Web-based Tool for Discovery of Latent Concepts},author = {Dalvi, Fahim and Durrani, Nadir and Sajjad, Hassan and Jaban, Tamim and Husaini, Mus{'}ab and Abbas, Ummar},booktitle = {Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations},month = may,year = {2023},address = {Dubrovnik, Croatia},publisher = {Association for Computational Linguistics},pages = {75--83},area = {Demos and Tools}}

@inproceedings{alam:2023:AAAI,title = {ConceptX: A Framework for Latent Concept Analysis},author = {Alam, Firoj and Dalvi, Fahim and Durrani, Nadir and Sajjad, Hassan and Khan and Rafae, Abdul and Xu, Jia},booktitle = {Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI, Poster presentation)},year = {2023},month = feb,pages = {16395-16397},area = {Demos and Tools}}