Datasets ডেটাসেট

@article{Ahmed_2026, title={BanglaRegionalTextCorpus: A curated dataset for four regional bangla dialects with standard Bangla and English translation}, volume={65}, ISSN={2352-3409}, url={http://dx.doi.org/10.1016/j.dib.2026.112585}, DOI={10.1016/j.dib.2026.112585}, journal={Data in Brief}, publisher={Elsevier BV}, author={Ahmed, Md. Tofael and Koli, Zannatul Mawa and Rahat, Azmain Mahtab and Akhter, Taslima and Ayman, Umme}, year={2026}, month=Apr, pages={112585} }

@inproceedings{sijan-etal-2026-banglasocialbench,
  title = "{B}angla{S}ocial{B}ench: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of {LLM}s in Bangladeshi Social Interaction",
  author = "Sijan, Tanvir Ahmed  and
    Rifat, S. M. Golam  and
    Partha, Pankaj  and
    Islam, Md. Tanjeed  and
    Anwar, Md Musfique",
  editor = "T.Y.S.S., Santosh  and
    Rodriguez, Juan Diego  and
    de Gibert, Ona",
  booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
  month = jul,
  year = "2026",
  address = "San Diego, California, United States",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2026.acl-srw.22/",
  doi = "10.18653/v1/2026.acl-srw.22",
  pages = "247--280",
  ISBN = "979-8-89176-393-7"
}

@misc{tabib2026bengaliloopcommunitybenchmarkslongform,
      title={Bengali-Loop: Community Benchmarks for Long-Form Bangla ASR and Speaker Diarization},
      author={H. M. Shadman Tabib and Istiak Ahmmed Rifti and Abdullah Muhammed Amimul Ehsan and Somik Dasgupta and Md Zim Mim Siddiqee Sowdha and Abrar Jahin Sarker and Md. Rafiul Islam Nijamy and Tanvir Hossain and Mst. Metaly Khatun and Munzer Mahmood and Rakesh Debnath and Gourab Biswas and Asif Karim and Wahid Al Azad Navid and Masnoon Muztahid and Fuad Ahmed Udoy and Shahad Shahriar Rahman and Md. Tashdiqur Rahman Shifat and Most. Sonia Khatun and Mushfiqur Rahman and Md. Miraj Hasan and Anik Saha and Mohammad Ninad Mahmud Nobo and Soumik Bhattacharjee and Tusher Bhomik and Ahmmad Nur Swapnil and Shahriar Kabir},
      year={2026},
      eprint={2602.14291},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2602.14291},
}

@misc{https://doi.org/10.17632/5wrm959d6f.1,
  doi = {10.17632/5WRM959D6F.1},
  url = {https://data.mendeley.com/datasets/5wrm959d6f/1},
  author = {Tahmid, Labib and Abedin, Istiak and Ahmed, Kawsar and Hassan Chowdhury , Zinedin and Sultana, Babe },
  keywords = {Computer Science, Artificial Intelligence, Cybersecurity, Natural Language Processing, Machine Learning},
  title = {BTTC - A Bangla Tri-class Text Corpus for Spam, Ham, and Promotional Messages},
  publisher = {Mendeley Data},
  year = {2026}
}

@article{Faisal_2026, title={Kothon: A large-scale dataset for machine translation of the Chittagonian and Sylheti dialects into standard Bangla}, volume={66}, ISSN={2352-3409}, url={http://dx.doi.org/10.1016/j.dib.2026.112789}, DOI={10.1016/j.dib.2026.112789}, journal={Data in Brief}, publisher={Elsevier BV}, author={Faisal, Md. Atique and Sadaf, Farhan and Chowdhury, Dipta and Azrof, H.M. and Tanmay, Monojit Paul}, year={2026}, month=June, pages={112789} }

@misc{hasan2026makehardheareasy,
      title={Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment},
      author={Sanjid Hasan and Risalat Labib and A H M Fuad and Bayazid Hasan},
      year={2026},
      eprint={2602.23070},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2602.23070},
}

@misc{eyasir2026nctbqalargescalebanglaeducational,
  title={NCTB-QA: A Large-Scale Bangla Educational Question Answering Dataset and Benchmarking Performance},
  author={Abrar Eyasir and Tahsin Ahmed and Muhammad Ibrahim},
  year={2026},
  eprint={2603.05462},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2603.05462}
}

@article{Rashid_2025, title={ALERT: A benchmark Bengali dataset for identifying and categorizing religiously aggressive texts}, volume={63}, ISSN={2352-3409}, url={http://dx.doi.org/10.1016/j.dib.2025.112094}, DOI={10.1016/j.dib.2025.112094}, journal={Data in Brief}, publisher={Elsevier BV}, author={Rashid, Suhana Binta and Piyas, Bibhas Roy Chowdhury and Rahman, Sadia and Preenon, Bijoy Roy Chowdhury}, year={2025}, month=Dec, pages={112094} }

@misc{paul2025ancholiknerbenchmarkdatasetbangla,
      title={ANCHOLIK-NER: A Benchmark Dataset for Bangla Regional Named Entity Recognition},
      author={Bidyarthi Paul and Faika Fairuj Preotee and Shuvashis Sarker and Shamim Rahim Refat and Shifat Islam and Tashreef Muhammad and Mohammad Ashraful Hoque and Shahriar Manzoor},
      year={2025},
      eprint={2502.11198},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      doi={https://doi.org/10.1371/journal.pone.0342786},
      url={https://arxiv.org/abs/2502.11198},
}

@inproceedings{hosain-morol-2025-b,
  title = {{B}-{REASO}: A Multi-Level Multi-Faceted {B}engali Evaluation Suite for Foundation Models},
  author = {Hosain, Md Tanzib and Morol, Md Kishor},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025},
  year = {2025},
  pages = {9260--9274},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.findings-emnlp.492/},
  doi = {10.18653/v1/2025.findings-emnlp.492}
}

@article{Siam_2026, title={BABSA: A large scale bangla aspect based sentiment analysis dataset}, volume={65}, ISSN={2352-3409}, url={http://dx.doi.org/10.1016/j.dib.2026.112604}, DOI={10.1016/j.dib.2026.112604}, journal={Data in Brief}, publisher={Elsevier BV}, author={Siam, M.F.R. and Wafa, Narmeen}, year={2026}, month=Apr, pages={112604} }

@inproceedings{shibu-etal-2025-scarcity,
    title = "From Scarcity to Capability: Empowering Fake News Detection in Low-Resource Languages with {LLM}s",
    author = "Shibu, Hrithik Majumdar  and
      Datta, Shrestha  and
      Miah, Md. Sumon  and
      Sami, Nasrullah  and
      Chowdhury, Mahruba Sharmin  and
      Islam, Md Saiful",
    editor = "Weerasinghe, Ruvan  and
      Anuradha, Isuri  and
      Sumanathilaka, Deshan",
    booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indo-Aryan and Dravidian Languages",
    month = jan,
    year = "2025",
    address = "Abu Dhabi",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.indonlp-1.12/",
    pages = "100--107"
}

@article{Sheikh_2026, title={Bangla-MedER: An annotated Bangla dataset for multi-type medical entity recognition from medical text}, volume={66}, ISSN={2352-3409}, url={http://dx.doi.org/10.1016/j.dib.2026.112705}, DOI={10.1016/j.dib.2026.112705}, journal={Data in Brief}, publisher={Elsevier BV}, author={Sheikh, Rubel and Rafiq, Shifat Ara and Hasan, Md. Mehedi and Ahmed, Shakil and Aurpa, Tanjim Taharat and Akter, Farzana}, year={2026}, month=June, pages={112705} }

@article{Rupa_2025, title={Bangla-ToCo: A context-aware dataset for Bengali toxic comment detection}, volume={63}, ISSN={2352-3409}, url={http://dx.doi.org/10.1016/j.dib.2025.112277}, DOI={10.1016/j.dib.2025.112277}, journal={Data in Brief}, publisher={Elsevier BV}, author={Rupa, Sayma Akter and Anwar, Md. Musfique and Ritu, Nadia Afrin and Arifin, Khandoker Nosiba}, year={2025}, month=Dec, pages={112277} }

@inproceedings{prama-etal-2025-banglamath,
    title = "{B}angla{MATH} : A {B}angla benchmark dataset for testing {LLM} mathematical reasoning at grades 6, 7, and 8",
    author = "Prama, Tabia Tanzin  and
      Danforth, Christopher M.  and
      Dodds, Peter",
    editor = "Valentino, Marco  and
      Ferreira, Deborah  and
      Thayaparan, Mokanarangan  and
      Ranaldi, Leonardo  and
      Freitas, Andre",
    booktitle = "Proceedings of The 3rd Workshop on Mathematical Natural Language Processing (MathNLP 2025)",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.mathnlp-main.10/",
    doi = "10.18653/v1/2025.mathnlp-main.10",
    pages = "134--149",
    ISBN = "979-8-89176-348-7"
}

@article{Biswas_2025, title={BanglaSarc3: A benchmark dataset for Bangla sarcasm detection from social media to advance Bangla NLP}, volume={62}, ISSN={2352-3409}, url={http://dx.doi.org/10.1016/j.dib.2025.111953}, DOI={10.1016/j.dib.2025.111953}, journal={Data in Brief}, publisher={Elsevier BV}, author={Biswas, Susmoy and Zahid, Md. Mostafizur Rahman and Rabeya, Mst Taposi and Abedin, Md. Minhazul and Bijoy, Md. Hasan Imam and Rahman, Md. Sadekur}, year={2025}, month=Oct, pages={111953} }

@inproceedings{raquib-etal-2025-banhate,
  title = "{B}an{H}ate: An Up-to-Date and Fine-Grained {B}angla Hate Speech Dataset",
  author = "Raquib, Faisal Hossain  and
    Mazumder, Akm Moshiur Rahman  and
    Fuad, Md Tahmid Hasan  and
    Ishmam, Md Farhan  and
    Fahim, Md",
  editor = "Alam, Firoj  and
    Kar, Sudipta  and
    Chowdhury, Shammur Absar  and
    Hassan, Naeemul  and
    Hoque, Enamul  and
    Laskar, Md Tahmid Rahman  and
    Mohiuddin, Tasnim  and
    Rony, Md Rashad Al Hasan",
  booktitle = "Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)",
  month = dec,
  year = "2025",
  address = "Mumbai, India",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2025.banglalp-1.19/",
  doi = "10.18653/v1/2025.banglalp-1.19",
  pages = "237--248",
  ISBN = "979-8-89176-314-2"
}

@inproceedings{mahtab-etal-2025-bannerd,
  title = "{B}an{NERD}: A Benchmark Dataset and Context-Driven Approach for {B}angla Named Entity Recognition",
  author = "Mahtab, Md. Motahar  and
    Khan, Faisal Ahamed  and
    Islam, Md. Ekramul  and
    Chowdhury, Md. Shahad Mahmud  and
    Chowdhury, Labib Imam  and
    Afrin, Sadia  and
    Ali, Hazrat  and
    Rashid, Mohammad Mamun Or  and
    Mohammed, Nabeel  and
    Amin, Mohammad Ruhul",
  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.380/",
  doi = "10.18653/v1/2025.findings-naacl.380",
  pages = "6822--6843",
  ISBN = "979-8-89176-195-7"
}

@inproceedings{haider-etal-2025-banth,
    title = "{B}an{TH}: A Multi-label Hate Speech Detection Dataset for Transliterated {B}angla",
    author = "Haider, Fabiha  and
      Shifat, Fariha Tanjim  and
      Ishmam, Md Farhan  and
      Sourove, Md Sakib Ul Rahman  and
      Barua, Deeparghya Dutta  and
      Fahim, Md  and
      Bhuiyan, Md Farhad Alam",
    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.403/",
    doi = "10.18653/v1/2025.findings-naacl.403",
    pages = "7232--7251",
    ISBN = "979-8-89176-195-7"
}

@inproceedings{joy-shatabda-2026-bnmmlu,
    title = "{B}n{MMLU}: Measuring Massive Multitask Language Understanding in {B}engali",
    author = "Joy, Saman Sarker  and
      Shatabda, Swakkhar",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-acl.593/",
    doi = "10.18653/v1/2026.findings-acl.593",
    pages = "12211--12230",
    ISBN = "979-8-89176-395-1"
}

@misc{paul2025leveraginglargelanguagemodels,
      title={Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning},
      author={Bidyarthi Paul and Jalisha Jashim Era and Mirazur Rahman Zim and Tahmid Sattar Aothoi and Faisal Muhammad Shah},
      year={2025},
      eprint={2505.21354},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.21354},
}

@inproceedings{fahim-etal-2024-banglatlit,
    title = "{B}angla{TL}it: A Benchmark Dataset for Back-Transliteration of {R}omanized {B}angla",
    author = "Fahim, Md  and
      Shifat, Fariha Tanjim  and
      Haider, Fabiha  and
      Barua, Deeparghya Dutta  and
      Sourove, MD Sakib Ul Rahman  and
      Ishmam, Md Farhan  and
      Bhuiyan, Md Farhad Alam",
    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.859/",
    doi = "10.18653/v1/2024.findings-emnlp.859",
    pages = "14656--14672"
}

@article{shafayat2024benqa,
  title = {{BE}n{QA}: A Question Answering and Reasoning Benchmark for {B}engali and {E}nglish},
  author = {Shafayat, Sheikh and others},
  journal = {arXiv preprint arXiv:2403.10900},
  year = {2024}
}

@inproceedings{alam-etal-2025-bnsentmix,
    title = "{B}n{S}ent{M}ix: A Diverse {B}engali-{E}nglish Code-Mixed Dataset for Sentiment Analysis",
    author = "Alam, Sadia  and
      Ishmam, Md Farhan  and
      Alvee, Navid Hasin  and
      Siddique, Md Shahnewaz  and
      Hossain, Md Azam  and
      Kamal, Abu Raihan Mostofa",
    editor = "Hettiarachchi, Hansi  and
      Ranasinghe, Tharindu  and
      Rayson, Paul  and
      Mitkov, Ruslan  and
      Gaber, Mohamed  and
      Premasiri, Damith  and
      Tan, Fiona Anting  and
      Uyangodage, Lasitha",
    booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.loreslm-1.4/",
    pages = "68--77"
}

@inproceedings{ardila-etal-2020-common,
    title = "Common Voice: A Massively-Multilingual Speech Corpus",
    author = "Ardila, Rosana  and
      Branson, Megan  and
      Davis, Kelly  and
      Kohler, Michael  and
      Meyer, Josh  and
      Henretty, Michael  and
      Morais, Reuben  and
      Saunders, Lindsay  and
      Tyers, Francis  and
      Weber, Gregor",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2020.lrec-1.520/",
    pages = "4218--4222",
    language = "eng",
    ISBN = "979-10-95546-34-4"
}

@inproceedings{raihan-etal-2024-emomix,
    title = "{E}mo{M}ix-3{L}: A Code-Mixed Dataset for {B}angla-{E}nglish-{H}indi for Emotion Detection",
    author = "Raihan, Nishat  and
      Goswami, Dhiman  and
      Mahmud, Antara  and
      Anastasopoulos, Antonios  and
      Zampieri, Marcos",
    editor = "Jha, Girish Nath  and
      L., Sobha  and
      Bali, Kalika  and
      Ojha, Atul Kr.",
    booktitle = "Proceedings of the 7th Workshop on Indian Language Data: Resources and Evaluation",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://aclanthology.org/2024.wildre-1.2/",
    pages = "11--16"
}

@misc{singh2025globalmmluunderstandingaddressing,
      title={Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation},
      author={Shivalika Singh and Angelika Romanou and Clémentine Fourrier and David I. Adelani and Jian Gang Ngui and Daniel Vila-Suero and Peerat Limkonchotiwat and Kelly Marchisio and Wei Qi Leong and Yosephine Susanto and Raymond Ng and Shayne Longpre and Wei-Yin Ko and Sebastian Ruder and Madeline Smith and Antoine Bosselut and Alice Oh and Andre F. T. Martins and Leshem Choshen and Daphne Ippolito and Enzo Ferrante and Marzieh Fadaee and Beyza Ermis and Sara Hooker},
      year={2025},
      eprint={2412.03304},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.03304},
}

@inproceedings{ahuja-etal-2024-megaverse,
    title = "{MEGAVERSE}: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks",
    author = "Ahuja, Sanchit  and
      Aggarwal, Divyanshu  and
      Gumma, Varun  and
      Watts, Ishaan  and
      Sathe, Ashutosh  and
      Ochieng, Millicent  and
      Hada, Rishav  and
      Jain, Prachi  and
      Ahmed, Mohamed  and
      Bali, Kalika  and
      Sitaram, Sunayana",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.143/",
    doi = "10.18653/v1/2024.naacl-long.143",
    pages = "2598--2637"
}

@inproceedings{Johora_Faria_2024, title={Motamot: A Dataset for Revealing the Supremacy of Large Language Models Over Transformer Models in Bengali Political Sentiment Analysis}, url={http://dx.doi.org/10.1109/TENSYMP61132.2024.10752197}, DOI={10.1109/tensymp61132.2024.10752197}, booktitle={2024 IEEE Region 10 Symposium (TENSYMP)}, publisher={IEEE}, author={Johora Faria, Fatema Tuj and Moin, Mukaffi Bin and Mumu, Rabeya Islam and Alam Abir, Md Mahabubul and Alfy, Abrar Nawar and Alam, Mohammad Shafiul}, year={2024}, month=Sept, pages={1–8} }

@article{Haque_2023, title={B-NER: A Novel Bangla Named Entity Recognition Dataset With Largest Entities and Its Baseline Evaluation}, volume={11}, ISSN={2169-3536}, url={http://dx.doi.org/10.1109/ACCESS.2023.3267746}, DOI={10.1109/access.2023.3267746}, journal={IEEE Access}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Haque, Md. Zahidul and Zaman, Sakib and Saurav, Jillur Rahman and Haque, Summit and Islam, Md. Saiful and Amin, Mohammad Ruhul}, year={2023}, pages={45194–45205} }

@inproceedings{kabir-etal-2023-banglabook,
    title = "{B}angla{B}ook: A Large-scale {B}angla Dataset for Sentiment Analysis from Book Reviews",
    author = "Kabir, Mohsinul  and
      Bin Mahfuz, Obayed  and
      Raiyan, Syed Rifat  and
      Mahmud, Hasan  and
      Hasan, Md Kamrul",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-acl.80/",
    doi = "10.18653/v1/2023.findings-acl.80",
    pages = "1237--1247"
}

@inproceedings{khan-etal-2023-banglachq,
    title = "{B}angla{CHQ}-Summ: An Abstractive Summarization Dataset for Medical Queries in {B}angla Conversational Speech",
    author = "Khan, Alvi  and
      Kamal, Fida  and
      Chowdhury, Mohammad Abrar  and
      Ahmed, Tasnim  and
      Laskar, Md Tahmid Rahman  and
      Ahmed, Sabbir",
    editor = "Alam, Firoj  and
      Kar, Sudipta  and
      Chowdhury, Shammur Absar  and
      Sadeque, Farig  and
      Amin, Ruhul",
    booktitle = "Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.banglalp-1.10/",
    doi = "10.18653/v1/2023.banglalp-1.10",
    pages = "85--93"
}

@article{Sultana_2025, title={BanSpEmo: a Bangla audio dataset for speech emotion recognition and its baseline evaluation}, volume={37}, ISSN={2502-4752}, url={http://dx.doi.org/10.11591/ijeecs.v37.i3.pp2044-2057}, DOI={10.11591/ijeecs.v37.i3.pp2044-2057}, number={3}, journal={Indonesian Journal of Electrical Engineering and Computer Science}, publisher={Institute of Advanced Engineering and Science}, author={Sultana, Babe and Hussain, Md Gulzar and Rahman, Mahmuda}, year={2025}, month=Mar, pages={2044} }

@article{Billah_2023, title={KBES: A dataset for realistic Bangla speech emotion recognition with intensity level}, volume={51}, ISSN={2352-3409}, url={http://dx.doi.org/10.1016/j.dib.2023.109741}, DOI={10.1016/j.dib.2023.109741}, journal={Data in Brief}, publisher={Elsevier BV}, author={Billah, Md. Masum and Sarker, Md. Likhon and Akhand, M. A. H.}, year={2023}, month=Dec, pages={109741} }

@inproceedings{goswami-etal-2023-offmix,
    title = "{O}ff{M}ix-3{L}: A Novel Code-Mixed Test Dataset in {B}angla-{E}nglish-{H}indi for Offensive Language Identification",
    author = "Goswami, Dhiman  and
      Raihan, Md Nishat  and
      Mahmud, Antara  and
      Anastasopoulos, Antonios  and
      Zampieri, Marcos",
    editor = "Ku, Lun-Wei  and
      Li, Cheng-Te",
    booktitle = "Proceedings of the 11th International Workshop on Natural Language Processing for Social Media",
    month = nov,
    year = "2023",
    address = "Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.socialnlp-1.3/",
    doi = "10.18653/v1/2023.socialnlp-1.3",
    pages = "21--27"
}

@misc{rakib2023oodspeechlargebengalispeech,
      title={OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking},
      author={Fazle Rabbi Rakib and Souhardya Saha Dip and Samiul Alam and Nazia Tasnim and Md. Istiak Hossain Shihab and Md. Nazmuddoha Ansary and Syed Mobassir Hossen and Marsia Haque Meghla and Mamunur Mamun and Farig Sadeque and Sayma Sultana Chowdhury and Tahsin Reasat and Asif Sushmit and Ahmed Imtiaz Humayun},
      year={2023},
      eprint={2305.09688},
      archivePrefix={arXiv},
      primaryClass={eess.AS},
      url={https://arxiv.org/abs/2305.09688},
}

@inproceedings{raihan-etal-2023-sentmix,
    title = "{S}ent{M}ix-3{L}: A Novel Code-Mixed Test Dataset in {B}angla-{E}nglish-{H}indi for Sentiment Analysis",
    author = "Raihan, Md Nishat  and
      Goswami, Dhiman  and
      Mahmud, Antara  and
      Anastasopoulos, Antonios  and
      Zampieri, Marcos",
    editor = "Wijaya, Derry  and
      Aji, Alham Fikri  and
      Vania, Clara  and
      Winata, Genta Indra  and
      Purwarianti, Ayu",
    booktitle = "Proceedings of the First Workshop in South East Asian Language Processing",
    month = nov,
    year = "2023",
    address = "Nusa Dua, Bali, Indonesia",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.sealp-1.6/",
    doi = "10.18653/v1/2023.sealp-1.6",
    pages = "79--84"
}

@inproceedings{raihan-etal-2023-offensive,
    title = "Offensive Language Identification in Transliterated and Code-Mixed {B}angla",
    author = "Raihan, Md Nishat  and
      Tanmoy, Umma  and
      Islam, Anika Binte  and
      North, Kai  and
      Ranasinghe, Tharindu  and
      Anastasopoulos, Antonios  and
      Zampieri, Marcos",
    editor = "Alam, Firoj  and
      Kar, Sudipta  and
      Chowdhury, Shammur Absar  and
      Sadeque, Farig  and
      Amin, Ruhul",
    booktitle = "Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.banglalp-1.1/",
    doi = "10.18653/v1/2023.banglalp-1.1",
    pages = "1--6"
}

@misc{faria2025vashantorlargescalemultilingualbenchmark,
      title={Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language},
      author={Fatema Tuj Johora Faria and Mukaffi Bin Moin and Ahmed Al Wase and Mehidi Ahmmed and Md. Rabius Sani and Tashreef Muhammad},
      year={2025},
      eprint={2311.11142},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2311.11142},
}

@inproceedings{akil-etal-2022-banglaparaphrase,
    title = "{B}angla{P}araphrase: A High-Quality {B}angla Paraphrase Dataset",
    author = "Akil, Ajwad  and
      Sultana, Najrin  and
      Bhattacharjee, Abhik  and
      Shahriyar, Rifat",
    editor = "He, Yulan  and
      Ji, Heng  and
      Li, Sujian  and
      Liu, Yang  and
      Chang, Chua-Hui",
    booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
    month = nov,
    year = "2022",
    address = "Online only",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.aacl-short.33/",
    doi = "10.18653/v1/2022.aacl-short.33",
    pages = "261--272"
}

@inproceedings{ekram-etal-2022-banglarqa,
    title = "{B}angla{RQA}: A Benchmark Dataset for Under-resourced {B}angla Language Reading Comprehension-based Question Answering with Diverse Question-Answer Types",
    author = "Ekram, Syed Mohammed Sartaj  and
      Rahman, Adham Arik  and
      Altaf, Md. Sajid  and
      Islam, Mohammed Saidul  and
      Rahman, Mehrab Mustafy  and
      Rahman, Md Mezbaur  and
      Hossain, Md Azam  and
      Kamal, Abu Raihan Mostofa",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-emnlp.186/",
    doi = "10.18653/v1/2022.findings-emnlp.186",
    pages = "2518--2532"
}

@article{Das_2022, title={BanglaSER: A speech emotion recognition dataset for the Bangla language}, volume={42}, ISSN={2352-3409}, url={http://dx.doi.org/10.1016/j.dib.2022.108091}, DOI={10.1016/j.dib.2022.108091}, journal={Data in Brief}, publisher={Elsevier BV}, author={Das, Rakesh Kumar and Islam, Nahidul and Ahmed, Md. Rayhan and Islam, Salekul and Shatabda, Swakkhar and Islam, A.K.M. Muzahidul}, year={2022}, month=June, pages={108091} }

@inproceedings{romim-etal-2022-bd,
    title = "{BD}-{SHS}: A Benchmark Dataset for Learning to Detect Online {B}angla Hate Speech in Different Social Contexts",
    author = "Romim, Nauros  and
      Ahmed, Mosahed  and
      Islam, Md Saiful  and
      Sen Sharma, Arnab  and
      Talukder, Hriteshwar  and
      Amin, Mohammad Ruhul",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
    month = jun,
    year = "2022",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2022.lrec-1.552/",
    pages = "5153--5162"
}

@Article{Iqbal2022,
author="Iqbal, MD. Asif
and Das, Avishek
and Sharif, Omar
and Hoque, Mohammed Moshiul
and Sarker, Iqbal H.",
title="BEmoC: A Corpus for Identifying Emotion in Bengali Texts",
journal="SN Computer Science",
year="2022",
month="Jan",
day="17",
volume="3",
number="2",
pages="135",
abstract="Emotion classification in text has growing interest among NLP experts due to the enormous availability of people's emotions and its emergence on various Web 2.0 applications/services. Emotion classification in the Bengali texts is also gradually being considered as an important task for sports, e-commerce, entertainments, and security applications. However, It is a very critical task to develop an automatic emotion classification system for low-resource languages such as, Bengali. Scarcity of resources and deficiency of benchmark corpora make the task more complicated. Thus, the development of a benchmark corpus is the prerequisite to develop an emotion classifier for Bengali texts. This paper describes the development of an emotional corpus (hereafter called `BEmoC') for classifying six emotions in Bengali texts. The corpus development process consists of four key steps: data crawling, pre-processing, labelling, and verification. A total of 7000 texts are labelled into six basic emotion categories such as anger, fear, surprise, sadness, joy, and disgust, respectively. Dataset evaluation with 0.969 Cohen's $\kappa$ score indicates the close agreement between the corpus annotators and the expert. The analysis of evaluation also represents that the distribution of emotion words obeys Zipf's law. Moreover, the results of BEmoC analysis shown in terms of coding reliability, emotion density, and most frequent emotion words, respectively.",
issn="2661-8907",
doi="10.1007/s42979-022-01028-w",
url="https://doi.org/10.1007/s42979-022-01028-w"
}

@misc{nllbteam2022languageleftbehindscaling,
      title={No Language Left Behind: Scaling Human-Centered Machine Translation},
      author={NLLB Team and Marta R. Costa-jussà and James Cross and Onur Çelebi and Maha Elbayad and Kenneth Heafield and Kevin Heffernan and Elahe Kalbassi and Janice Lam and Daniel Licht and Jean Maillard and Anna Sun and Skyler Wang and Guillaume Wenzek and Al Youngblood and Bapi Akula and Loic Barrault and Gabriel Mejia Gonzalez and Prangthip Hansanti and John Hoffman and Semarley Jarrett and Kaushik Ram Sadagopan and Dirk Rowe and Shannon Spruit and Chau Tran and Pierre Andrews and Necip Fazil Ayan and Shruti Bhosale and Sergey Edunov and Angela Fan and Cynthia Gao and Vedanuj Goswami and Francisco Guzmán and Philipp Koehn and Alexandre Mourachko and Christophe Ropers and Safiyyah Saleem and Holger Schwenk and Jeff Wang},
      year={2022},
      eprint={2207.04672},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2207.04672},
}

@inproceedings{malmasi-etal-2022-semeval,
    title = "{S}em{E}val-2022 Task 11: Multilingual Complex Named Entity Recognition ({M}ulti{C}o{NER})",
    author = "Malmasi, Shervin  and
      Fang, Anjie  and
      Fetahu, Besnik  and
      Kar, Sudipta  and
      Rokhlenko, Oleg",
    editor = "Emerson, Guy  and
      Schluter, Natalie  and
      Stanovsky, Gabriel  and
      Kumar, Ritesh  and
      Palmer, Alexis  and
      Schneider, Nathan  and
      Singh, Siddharth  and
      Ratan, Shyam",
    booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.semeval-1.196/",
    doi = "10.18653/v1/2022.semeval-1.196",
    pages = "1412--1437"
}

@misc{ahmad2022potrikarawbalancednewspaper,
      title={Potrika: Raw and Balanced Newspaper Datasets in the Bangla Language with Eight Topics and Five Attributes},
      author={Istiak Ahmad and Fahad AlQurashi and Rashid Mehmood},
      year={2022},
      eprint={2210.09389},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2210.09389},
}

@article{ramesh-etal-2022-samanantar,
    title = "Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 {I}ndic Languages",
    author = "Ramesh, Gowtham  and
      Doddapaneni, Sumanth  and
      Bheemaraj, Aravinth  and
      Jobanputra, Mayank  and
      AK, Raghavan  and
      Sharma, Ajitesh  and
      Sahoo, Sujit  and
      Diddee, Harshita  and
      J, Mahalakshmi  and
      Kakwani, Divyanshu  and
      Kumar, Navneet  and
      Pradeep, Aswin  and
      Nagaraj, Srihari  and
      Deepak, Kumar  and
      Raghavan, Vivek  and
      Kunchukuttan, Anoop  and
      Kumar, Pratyush  and
      Khapra, Mitesh Shantadevi",
    editor = "Roark, Brian  and
      Nenkova, Ani",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "10",
    year = "2022",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2022.tacl-1.9/",
    doi = "10.1162/tacl_a_00452",
    pages = "145--162"
}

@InProceedings{10.1007/978-981-33-4673-4_4,
author="Bhattacharjee, Prithwiraj
and Mallick, Avi
and Saiful Islam, Md.
and Marium-E-Jannat",
editor="Kaiser, M. Shamim
and Bandyopadhyay, Anirban
and Mahmud, Mufti
and Ray, Kanad",
title="Bengali Abstractive News Summarization (BANS): A Neural Attention Approach",
booktitle="Proceedings of International Conference on Trends in Computational and Cognitive Engineering",
year="2021",
publisher="Springer Singapore",
address="Singapore",
pages="41--51",
abstract="Bhattacharjee, PrithwirajMallick, AviSaiful Islam, Md.Marium-E-JannatAbstractive summarization is the process of generating novel sentences based on the information extracted from the original text document while retaining the context. Due to abstractive summarization's underlying complexities, most of the past research work has been done on the extractive summarization approach. Nevertheless, with the triumph of the sequence-to-sequence (seq2seq) model, abstractive summarization becomes more viable. Although a significant number of notable research has been done in the English language based on abstractive summarization, only a couple of works have been done on Bengali abstractive news summarization (BANS). In this article, we presented a seq2seq based Long Short-Term Memory (LSTM) network model with attention at encoder-decoder. Our proposed system deploys a local attention-based model that produces a long sequence of words with lucid and human-like generated sentences with noteworthy information of the original document. We also prepared a dataset of more than 19 k articles and corresponding human-written summaries collected from bangla.bdnews24.com (https://bangla.bdnews24.com/) which is till now the most extensive dataset for Bengali news document summarization and publicly published in Kaggle (https://www.kaggle.com/prithwirajsust/bengali-news-summarization-dataset) We evaluated our model qualitatively and quantitatively and compared it with other published results. It showed significant improvement in terms of human evaluation scores with state-of-the-art approaches for BANS.",
isbn="978-981-33-4673-4"
}

@inproceedings{islam-etal-2021-sentnob-dataset,
    title = "{S}ent{N}o{B}: A Dataset for Analysing Sentiment on Noisy {B}angla Texts",
    author = "Islam, Khondoker Ittehadul  and
      Kar, Sudipta  and
      Islam, Md Saiful  and
      Amin, Mohammad Ruhul",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.findings-emnlp.278/",
    doi = "10.18653/v1/2021.findings-emnlp.278",
    pages = "3265--3271"
}

@inproceedings{bhattacharjee-etal-2022-banglabert,
    title = "{B}angla{BERT}: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in {B}angla",
    author = "Bhattacharjee, Abhik  and
      Hasan, Tahmid  and
      Ahmad, Wasi  and
      Mubasshir, Kazi Samin  and
      Islam, Md Saiful  and
      Iqbal, Anindya  and
      Rahman, M. Sohel  and
      Shahriyar, Rifat",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    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.98/",
    doi = "10.18653/v1/2022.findings-naacl.98",
    pages = "1318--1327"
}

@article{10.1371/journal.pone.0250173,
    doi = {10.1371/journal.pone.0250173},
    author = {Sultana, Sadia AND Rahman, M. Shahidur AND Selim, M. Reza AND Iqbal, M. Zafar},
    journal = {PLOS ONE},
    publisher = {Public Library of Science},
    title = {SUST Bangla Emotional Speech Corpus (SUBESCO): An audio-only emotional speech corpus for Bangla},
    year = {2021},
    month = {04},
    volume = {16},
    url = {https://doi.org/10.1371/journal.pone.0250173},
    pages = {1-27},
    abstract = {SUBESCO is an audio-only emotional speech corpus for Bangla language. The total duration of the corpus is in excess of 7 hours containing 7000 utterances, and it is the largest emotional speech corpus available for this language. Twenty native speakers participated in the gender-balanced set, each recording of 10 sentences simulating seven targeted emotions. Fifty university students participated in the evaluation of this corpus. Each audio clip of this corpus, except those of Disgust emotion, was validated four times by male and female raters. Raw hit rates and unbiased rates were calculated producing scores above chance level of responses. Overall recognition rate was reported to be above 70% for human perception tests. Kappa statistics and intra-class correlation coefficient scores indicated high-level of inter-rater reliability and consistency of this corpus evaluation. SUBESCO is an Open Access database, licensed under Creative Common Attribution 4.0 International, and can be downloaded free of charge from the web link: https://doi.org/10.5281/zenodo.4526477.},
    number = {4},

}

@misc{11234/1-4611,
             title = {Universal Dependencies 2.9},
 author = {Zeman, Daniel and Nivre, Joakim and Abrams, Mitchell and Ackermann, Elia and Aepli, No{\"e}mi and Aghaei, Hamid and Agi{\'c}, {\v Z}eljko and Ahmadi, Amir and Ahrenberg, Lars and Ajede, Chika Kennedy and Aleksandravi{\v c}i{\=u}t{\.e}, Gabriel{\.e} and Alfina, Ika and Antonsen, Lene and Aplonova, Katya and Aquino, Angelina and Aragon, Carolina and Aranzabe, Maria Jesus and Ar{\i}can, Bilge Nas and Arnard{\'o}ttir, {\t H}{\'o}runn and Arutie, Gashaw and Arwidarasti, Jessica Naraiswari and Asahara, Masayuki and Aslan, Deniz Baran and Ateyah, Luma and Atmaca, Furkan and Attia, Mohammed and Atutxa, Aitziber and Augustinus, Liesbeth and Badmaeva, Elena and Balasubramani, Keerthana and Ballesteros, Miguel and Banerjee, Esha and Bank, Sebastian and Barbu Mititelu, Verginica and Barkarson, Starkaður and Basile, Rodolfo and Basmov, Victoria and Batchelor, Colin and Bauer, John and Bedir, Seyyit Talha and Bengoetxea, Kepa and Berk, G{\"o}zde and Berzak, Yevgeni and Bhat, Irshad Ahmad and Bhat, Riyaz Ahmad and Biagetti, Erica and Bick, Eckhard and Bielinskien{\.e}, Agn{\.e} and Bjarnad{\'o}ttir, Krist{\'{\i}}n and Blokland, Rogier and Bobicev, Victoria and Boizou, Lo{\"{\i}}c and Borges V{\"o}lker, Emanuel and B{\"o}rstell, Carl and Bosco, Cristina and Bouma, Gosse and Bowman, Sam and Boyd, Adriane and Braggaar, Anouck and Brokait{\.e}, Kristina and Burchardt, Aljoscha and Candito, Marie and Caron, Bernard and Caron, Gauthier and Cassidy, Lauren and Cavalcanti, Tatiana and Cebiro{\u g}lu Eryi{\u g}it, G{\"u}l{\c s}en and Cecchini, Flavio Massimiliano and Celano, Giuseppe G. A. and {\v C}{\'e}pl{\"o}, Slavom{\'{\i}}r and Cesur, Neslihan and Cetin, Savas and {\c C}etino{\u g}lu, {\"O}zlem and Chalub, Fabricio and Chauhan, Shweta and Chi, Ethan and Chika, Taishi and Cho, Yongseok and Choi, Jinho and Chun, Jayeol and Chung, Juyeon and Cignarella, Alessandra T. and Cinkov{\'a}, Silvie and Collomb, Aur{\'e}lie and {\c C}{\"o}ltekin, {\c C}a{\u g}r{\i} and Connor, Miriam and Courtin, Marine and Cristescu, Mihaela and Daniel, Philemon and Davidson, Elizabeth and de Marneffe, Marie-Catherine and de Paiva, Valeria and Derin, Mehmet Oguz and de Souza, Elvis and Diaz de Ilarraza, Arantza and Dickerson, Carly and Dinakaramani, Arawinda and Di Nuovo, Elisa and Dione, Bamba and Dirix, Peter and Dobrovoljc, Kaja and Dozat, Timothy and Droganova, Kira and Dwivedi, Puneet and Eckhoff, Hanne and Eiche, Sandra and Eli, Marhaba and Elkahky, Ali and Ephrem, Binyam and Erina, Olga and Erjavec, Toma{\v z} and Etienne, Aline and Evelyn, Wograine and Facundes, Sidney and Farkas, Rich{\'a}rd and Ferdaousi, Jannatul and Fernanda, Mar{\'{\i}}lia and Fernandez Alcalde, Hector and Foster, Jennifer and Freitas, Cl{\'a}udia and Fujita, Kazunori and Gajdo{\v s}ov{\'a}, Katar{\'{\i}}na and Galbraith, Daniel and Garcia, Marcos and G{\"a}rdenfors, Moa and Garza, Sebastian and Gerardi, Fabr{\'{\i}}cio Ferraz and Gerdes, Kim and Ginter, Filip and Godoy, Gustavo and Goenaga, Iakes and Gojenola, Koldo and G{\"o}k{\i}rmak, Memduh and Goldberg, Yoav and G{\'o}mez Guinovart, Xavier and Gonz{\'a}lez Saavedra, Berta and Grici{\=u}t{\.e}, Bernadeta and Grioni, Matias and Grobol, Lo{\"{\i}}c and Gr{\=u}z{\={\i}}tis, Normunds and Guillaume, Bruno and Guillot-Barbance, C{\'e}line and G{\"u}ng{\"o}r, Tunga and Habash, Nizar and Hafsteinsson, Hinrik and Haji{\v c}, Jan and Haji{\v c} jr., Jan and H{\"a}m{\"a}l{\"a}inen, Mika and H{\`a} M{\~y}, Linh and Han, Na-Rae and Hanifmuti, Muhammad Yudistira and Hardwick, Sam and Harris, Kim and Haug, Dag and Heinecke, Johannes and Hellwig, Oliver and Hennig, Felix and Hladk{\'a}, Barbora and Hlav{\'a}{\v c}ov{\'a}, Jaroslava and Hociung, Florinel and Hohle, Petter and Huber, Eva and Hwang, Jena and Ikeda, Takumi and Ingason, Anton Karl and Ion, Radu and Irimia, Elena and Ishola, {\d O}l{\'a}j{\'{\i}}d{\'e} and Ito, Kaoru and Jannat, Siratun and Jel{\'{\i}}nek, Tom{\'a}{\v s} and Jha, Apoorva and Johannsen, Anders and J{\'o}nsd{\'o}ttir, Hildur and J{\o}rgensen, Fredrik and Juutinen, Markus and K, Sarveswaran and Ka{\c s}{\i}kara, H{\"u}ner and Kaasen, Andre and Kabaeva, Nadezhda and Kahane, Sylvain and Kanayama, Hiroshi and Kanerva, Jenna and Kara, Neslihan and Katz, Boris and Kayadelen, Tolga and Kenney, Jessica and Kettnerov{\'a}, V{\'a}clava and Kirchner, Jesse and Klementieva, Elena and Klyachko, Elena and K{\"o}hn, Arne and K{\"o}ksal, Abdullatif and Kopacewicz, Kamil and Korkiakangas, Timo and K{\"o}se, Mehmet and Kotsyba, Natalia and Kovalevskait{\.e}, Jolanta and Krek, Simon and Krishnamurthy, Parameswari and K{\"u}bler, Sandra and Kuyruk{\c c}u, O{\u g}uzhan and Kuzgun, Asl{\i} and Kwak, Sookyoung and Laippala, Veronika and Lam, Lucia and Lambertino, Lorenzo and Lando, Tatiana and Larasati, Septina Dian and Lavrentiev, Alexei and Lee, John and L{\^e} H{\`{\^o}}ng, Phương and Lenci, Alessandro and Lertpradit, Saran and Leung, Herman and Levina, Maria and Li, Cheuk Ying and Li, Josie and Li, Keying and Li, Yuan and Lim, {KyungTae} and Lima Padovani, Bruna and Lind{\'e}n, Krister and Ljube{\v s}i{\'c}, Nikola and Loginova, Olga and Lusito, Stefano and Luthfi, Andry and Luukko, Mikko and Lyashevskaya, Olga and Lynn, Teresa and Macketanz, Vivien and Mahamdi, Menel and Maillard, Jean and Makazhanov, Aibek and Mandl, Michael and Manning, Christopher and Manurung, Ruli and Mar{\c s}an, B{\"u}{\c s}ra and M{\u a}r{\u a}nduc, C{\u a}t{\u a}lina and Mare{\v c}ek, David and Marheinecke, Katrin and Mart{\'{\i}}nez Alonso, H{\'e}ctor and Mart{\'{\i}}n-Rodr{\'{\i}}guez, Lorena and Martins, Andr{\'e} and Ma{\v s}ek, Jan and Matsuda, Hiroshi and Matsumoto, Yuji and Mazzei, Alessandro and {McDonald}, Ryan and {McGuinness}, Sarah and Mendon{\c c}a, Gustavo and Merzhevich, Tatiana and Miekka, Niko and Mischenkova, Karina and Misirpashayeva, Margarita and Missil{\"a}, Anna and Mititelu, C{\u a}t{\u a}lin and Mitrofan, Maria and Miyao, Yusuke and Mojiri Foroushani, {AmirHossein} and Moln{\'a}r, Judit and Moloodi, Amirsaeid and Montemagni, Simonetta and More, Amir and Moreno Romero, Laura and Moretti, Giovanni and Mori, Keiko Sophie and Mori, Shinsuke and Morioka, Tomohiko and Moro, Shigeki and Mortensen, Bjartur and Moskalevskyi, Bohdan and Muischnek, Kadri and Munro, Robert and Murawaki, Yugo and M{\"u}{\"u}risep, Kaili and Nainwani, Pinkey and Nakhl{\'e}, Mariam and Navarro Hor{\~n}iacek, Juan Ignacio and Nedoluzhko, Anna and Ne{\v s}pore-B{\=e}rzkalne, Gunta and Nevaci, Manuela and Nguy{\~{\^e}}n Th{\d i}, Lương and Nguy{\~{\^e}}n Th{\d i} Minh, Huy{\`{\^e}}n and Nikaido, Yoshihiro and Nikolaev, Vitaly and Nitisaroj, Rattima and Nourian, Alireza and Nurmi, Hanna and Ojala, Stina and Ojha, Atul Kr. and Ol{\'u}{\`o}kun, Ad{\'e}day{\d o}̀ and Omura, Mai and Onwuegbuzia, Emeka and Osenova, Petya and {\"O}stling, Robert and {\O}vrelid, Lilja and {\"O}zate{\c s}, {\c S}aziye Bet{\"u}l and {\"O}z{\c c}elik, Merve and {\"O}zg{\"u}r, Arzucan and {\"O}zt{\"u}rk Ba{\c s}aran, Balk{\i}z and Park, Hyunji Hayley and Partanen, Niko and Pascual, Elena and Passarotti, Marco and Patejuk, Agnieszka and Paulino-Passos, Guilherme and Peljak-{\L}api{\'n}ska, Angelika and Peng, Siyao and Perez, Cenel-Augusto and Perkova, Natalia and Perrier, Guy and Petrov, Slav and Petrova, Daria and Phelan, Jason and Piitulainen, Jussi and Pirinen, Tommi A and Pitler, Emily and Plank, Barbara and Poibeau, Thierry and Ponomareva, Larisa and Popel, Martin and Pretkalni{\c n}a, Lauma and Pr{\'e}vost, Sophie and Prokopidis, Prokopis and Przepi{\'o}rkowski, Adam and Puolakainen, Tiina and Pyysalo, Sampo and Qi, Peng and R{\"a}{\"a}bis, Andriela and Rademaker, Alexandre and Rahoman, Mizanur and Rama, Taraka and Ramasamy, Loganathan and Ramisch, Carlos and Rashel, Fam and Rasooli, Mohammad Sadegh and Ravishankar, Vinit and Real, Livy and Rebeja, Petru and Reddy, Siva and Regnault, Mathilde and Rehm, Georg and Riabov, Ivan and Rie{\ss}ler, Michael and Rimkut{\.e}, Erika and Rinaldi, Larissa and Rituma, Laura and Rizqiyah, Putri and Rocha, Luisa and R{\"o}gnvaldsson, Eir{\'{\i}}kur and Romanenko, Mykhailo and Rosa, Rudolf and Roșca, Valentin and Rovati, Davide and Rudina, Olga and Rueter, Jack and R{\'u}narsson, Kristj{\'a}n and Sadde, Shoval and Safari, Pegah and Sagot, Beno{\^{\i}}t and Sahala, Aleksi and Saleh, Shadi and Salomoni, Alessio and Samard{\v z}i{\'c}, Tanja and Samson, Stephanie and Sanguinetti, Manuela and San{\i}yar, Ezgi and S{\"a}rg, Dage and Saul{\={\i}}te, Baiba and Sawanakunanon, Yanin and Saxena, Shefali and Scannell, Kevin and Scarlata, Salvatore and Schneider, Nathan and Schuster, Sebastian and Schwartz, Lane and Seddah, Djam{\'e} and Seeker, Wolfgang and Seraji, Mojgan and Shahzadi, Syeda and Shen, Mo and Shimada, Atsuko and Shirasu, Hiroyuki and Shishkina, Yana and Shohibussirri, Muh and Sichinava, Dmitry and Siewert, Janine and Sigurðsson, Einar Freyr and Silveira, Aline and Silveira, Natalia and Simi, Maria and Simionescu, Radu and Simk{\'o}, Katalin and {\v S}imkov{\'a}, M{\'a}ria and Simov, Kiril and Skachedubova, Maria and Smith, Aaron and Soares-Bastos, Isabela and Sourov, Shafi and Spadine, Carolyn and Sprugnoli, Rachele and Steingr{\'{\i}}msson, Stein{\t h}{\'o}r and Stella, Antonio and Straka, Milan and Strickland, Emmett and Strnadov{\'a}, Jana and Suhr, Alane and Sulestio, Yogi Lesmana and Sulubacak, Umut and Suzuki, Shingo and Sz{\'a}nt{\'o}, Zsolt and Taguchi, Chihiro and Taji, Dima and Takahashi, Yuta and Tamburini, Fabio and Tan, Mary Ann C. and Tanaka, Takaaki and Tanaya, Dipta and Tella, Samson and Tellier, Isabelle and Testori, Marinella and Thomas, Guillaume and Torga, Liisi and Toska, Marsida and Trosterud, Trond and Trukhina, Anna and Tsarfaty, Reut and T{\"u}rk, Utku and Tyers, Francis and Uematsu, Sumire and Untilov, Roman and Ure{\v s}ov{\'a}, Zde{\v n}ka and Uria, Larraitz and Uszkoreit, Hans and Utka, Andrius and Vajjala, Sowmya and van der Goot, Rob and Vanhove, Martine and van Niekerk, Daniel and van Noord, Gertjan and Varga, Viktor and Villemonte de la Clergerie, Eric and Vincze, Veronika and Vlasova, Natalia and Wakasa, Aya and Wallenberg, Joel C. and Wallin, Lars and Walsh, Abigail and Wang, Jing Xian and Washington, Jonathan North and Wendt, Maximilan and Widmer, Paul and Wijono, Sri Hartati and Williams, Seyi and Wir{\'e}n, Mats and Wittern, Christian and Woldemariam, Tsegay and Wong, Tak-sum and Wr{\'o}blewska, Alina and Yako, Mary and Yamashita, Kayo and Yamazaki, Naoki and Yan, Chunxiao and Yasuoka, Koichi and Yavrumyan, Marat M. and Yenice, Arife Bet{\"u}l and Y{\i}ld{\i}z, Olcay Taner and Yu, Zhuoran and Yuliawati, Arlisa and {\v Z}abokrtsk{\'y}, Zden{\v e}k and Zahra, Shorouq and Zeldes, Amir and Zhou, He and Zhu, Hanzhi and Zhuravleva, Anna and Ziane, Rayan},
 url = {http://hdl.handle.net/11234/1-4611},
 note = {{LINDAT}/{CLARIAH}-{CZ} digital library at the Institute of Formal and Applied Linguistics ({{\'U}FAL})},
 copyright = {Licence Universal Dependencies v2.9},
 year = {2021}
}

@inproceedings{hasan-etal-2021-xl,
  title = {{XL}-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages},
  author = {Hasan, Tahmid and Bhattacharjee, Abhik and others},
  booktitle = {Findings of ACL},
  year = {2021}
}

@inproceedings{hossain-etal-2020-banfakenews,
    title = "{B}an{F}ake{N}ews: A Dataset for Detecting Fake News in {B}angla",
    author = "Hossain, Md Zobaer  and
      Rahman, Md Ashraful  and
      Islam, Md Saiful  and
      Kar, Sudipta",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://aclanthology.org/2020.lrec-1.349/",
    pages = "2862--2871",
    language = "eng",
    ISBN = "979-10-95546-34-4"
}

@inproceedings{hasan-etal-2020-low,
  title = {Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for {B}engali-{E}nglish Machine Translation},
  author = {Hasan, Tahmid and Bhattacharjee, Abhik and others},
  booktitle = {EMNLP},
  year = {2020}
}

@misc{karim2020classificationbenchmarksunderresourcedbengali,
      title={Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network},
      author={Md. Rezaul Karim and Bharathi Raja Chakravarthi and John P. McCrae and Michael Cochez},
      year={2020},
      eprint={2004.07807},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2004.07807},
}

@article{clark-etal-2020-tydi,
    title = "{T}y{D}i {QA}: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages",
    author = "Clark, Jonathan H.  and
      Choi, Eunsol  and
      Collins, Michael  and
      Garrette, Dan  and
      Kwiatkowski, Tom  and
      Nikolaev, Vitaly  and
      Palomaki, Jennimaria",
    editor = "Johnson, Mark  and
      Roark, Brian  and
      Nenkova, Ani",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "8",
    year = "2020",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2020.tacl-1.30/",
    doi = "10.1162/tacl_a_00317",
    pages = "454--470"
}

@inproceedings{rahimi-etal-2019-massively,
    title = "Massively Multilingual Transfer for {NER}",
    author = "Rahimi, Afshin  and
      Li, Yuan  and
      Cohn, Trevor",
    editor = "Korhonen, Anna  and
      Traum, David  and
      M{\`a}rquez, Llu{\'i}s",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/P19-1015/",
    doi = "10.18653/v1/P19-1015",
    pages = "151--164"
}

@article{Rahman_2018, title={Datasets for Aspect-Based Sentiment Analysis in Bangla and Its Baseline Evaluation}, volume={3}, ISSN={2306-5729}, url={http://dx.doi.org/10.3390/data3020015}, DOI={10.3390/data3020015}, number={2}, journal={Data}, publisher={MDPI AG}, author={Rahman, Md. Atikur and Kumar Dey, Emon}, year={2018}, month=May, pages={15} }

@inproceedings{Tanvir_Alam_2018, title={BARD: Bangla Article Classification Using a New Comprehensive Dataset}, url={http://dx.doi.org/10.1109/ICBSLP.2018.8554382}, DOI={10.1109/icbslp.2018.8554382}, booktitle={2018 International Conference on Bangla Speech and Language Processing (ICBSLP)}, publisher={IEEE}, author={Tanvir Alam, Md and Mofijul Islam, Md}, year={2018}, month=Sept, pages={1–5} }

@inproceedings{Kjartansson_2018, series={sltu_2018}, title={Crowd-Sourced Speech Corpora for Javanese, Sundanese, Sinhala, Nepali, and Bangladeshi Bengali}, url={http://dx.doi.org/10.21437/SLTU.2018-11}, DOI={10.21437/sltu.2018-11}, booktitle={6th Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU 2018)}, publisher={ISCA}, author={Kjartansson, Oddur and Sarin, Supheakmungkol and Pipatsrisawat, Knot and Jansche, Martin and Ha, Linne}, year={2018}, month=Aug, pages={52–55}, collection={sltu_2018} }