Publications

2023

1. NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages

   Samuel Cahyawijaya, Holy Lovenia, Fajri Koto, Dea Adhista, Emmanuel Dave, Sarah Oktavianti, Salsabil Maulana Akbar, Jhonson Lee, Nuur Shadieq, Tjeng Wawan Cenggoro, Hanung Wahyuning Linuwih, Bryan Wilie, Galih Pradipta Muridan, Genta Indra Winata, David Moeljadi, Alham Fikri Aji, Ayu Purwarianti, and Pascale Fung.

   . 2023.

   arXiv Bib

   @misc{cahyawijaya2023nusawrites,
     title = {{NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages}},
     author = {Cahyawijaya, Samuel and Lovenia, Holy and Koto, Fajri and Adhista, Dea and Dave, Emmanuel and Oktavianti, Sarah and Akbar, Salsabil Maulana and Lee, Jhonson and Shadieq, Nuur and Cenggoro, Tjeng Wawan and Linuwih, Hanung Wahyuning and Wilie, Bryan and Muridan, Galih Pradipta and Winata, Genta Indra and Moeljadi, David and Aji, Alham Fikri and Purwarianti, Ayu and Fung, Pascale},
     year = {2023},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
   }

2. IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems

   Muhammad Dehan Al Kautsar, Rahmah Khoirussyifa’ Nurdini,  Samuel Cahyawijaya, Genta Indra Winata, and Ayu Purwarianti.

   . 2023.

   arXiv Bib

   @misc{kautsar2023indotod,
     title = {IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems},
     author = {Kautsar, Muhammad Dehan Al and Nurdini, Rahmah Khoirussyifa' and Cahyawijaya, Samuel and Winata, Genta Indra and Purwarianti, Ayu},
     year = {2023},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
   }

3. Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models

   Holy Lovenia, Wenliang Dai,  Samuel Cahyawijaya, Ziwei Ji, and Pascale Fung.

   . 2023.

   arXiv Bib

   @misc{lovenia2023negative,
     title = {Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models},
     author = {Lovenia, Holy and Dai, Wenliang and Cahyawijaya, Samuel and Ji, Ziwei and Fung, Pascale},
     year = {2023},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
   }

4. InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems

   Willy Chung,  Samuel Cahyawijaya, Bryan Wilie, Holy Lovenia, and Pascale Fung.

   . 2023.

   arXiv Bib

   @misc{chung2023instructtods,
     title = {InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems},
     author = {Chung, Willy and Cahyawijaya, Samuel and Wilie, Bryan and Lovenia, Holy and Fung, Pascale},
     year = {2023},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
   }

5. A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity

   Yejin Bang,  Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, and others.

   arXiv preprint arXiv:2302.04023. 2023.

   arXiv Bib

   @article{bang2023multitask,
     title = {{A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity}},
     author = {Bang, Yejin and Cahyawijaya, Samuel and Lee, Nayeon and Dai, Wenliang and Su, Dan and Wilie, Bryan and Lovenia, Holy and Ji, Ziwei and Yu, Tiezheng and Chung, Willy and others},
     year = {2023},
     journal = {arXiv preprint arXiv:2302.04023},
   }

6. Biomedical Image Reconstruction: A Survey

   Samuel Cahyawijaya.

   arXiv preprint arXiv:2301.11813. 2023.

   arXiv Bib

   @article{cahyawijaya2023biomedical,
     title = {{Biomedical Image Reconstruction: A Survey}},
     author = {Cahyawijaya, Samuel},
     year = {2023},
     journal = {arXiv preprint arXiv:2301.11813},
   }

7. Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition

   Samuel Cahyawijaya, Holy Lovenia, Willy Chung, Rita Frieske, Zihan Liu, and Pascale Fung.

   In INTERSPEECH 2023, 24th Annual Conference of the International Speech Communication Association, Dublin, Ireland, 20-24 August 2023. 2023.

   arXiv Bib

   @inproceedings{cahyawijaya2023cross,
     title = {{Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition}},
     author = {Cahyawijaya, Samuel and Lovenia, Holy and Chung, Willy and Frieske, Rita and Liu, Zihan and Fung, Pascale},
     year = {2023},
     booktitle = {INTERSPEECH 2023, 24th Annual Conference of the International Speech Communication Association, Dublin, Ireland, 20-24 August 2023},
     publisher = {{ISCA}},
   }

8. GlobalBench: A Benchmark for Global Progress in Natural Language Processing

   Yueqi Song, Catherine Cui, Simran Khanuja, Pengfei Liu, Fahim Faisal, Alissa Ostapenko, Genta Indra Winata, Alham Fikri Aji,  Samuel Cahyawijaya, Yulia Tsvetkov, and others.

   arXiv preprint arXiv:2305.14716. 2023.

   arXiv Bib

   @article{song2023globalbench,
     title = {{GlobalBench: A Benchmark for Global Progress in Natural Language Processing}},
     author = {Song, Yueqi and Cui, Catherine and Khanuja, Simran and Liu, Pengfei and Faisal, Fahim and Ostapenko, Alissa and Winata, Genta Indra and Aji, Alham Fikri and Cahyawijaya, Samuel and Tsvetkov, Yulia and others},
     year = {2023},
     journal = {arXiv preprint arXiv:2305.14716},
   }

9. InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning

   Samuel Cahyawijaya, Holy Lovenia, Tiezheng Yu, Willy Chung, and Pascale Fung.

   arXiv preprint arXiv:2305.13627. 2023.

   arXiv Bib

   @article{cahyawijaya2023instruct,
     title = {{InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning}},
     author = {Cahyawijaya, Samuel and Lovenia, Holy and Yu, Tiezheng and Chung, Willy and Fung, Pascale},
     year = {2023},
     journal = {arXiv preprint arXiv:2305.13627},
   }

10. Multi-lingual and Multi-cultural Figurative Language Understanding

    Anubha Kabra, Emmy Liu, Simran Khanuja, Alham Fikri Aji, Genta Indra Winata,  Samuel Cahyawijaya, Anuoluwapo Aremu, Perez Ogayo, and Graham Neubig.

    arXiv preprint arXiv:2305.16171. 2023.

    arXiv Bib

    @article{kabra2023multi,
      title = {{Multi-lingual and Multi-cultural Figurative Language Understanding}},
      author = {Kabra, Anubha and Liu, Emmy and Khanuja, Simran and Aji, Alham Fikri and Winata, Genta Indra and Cahyawijaya, Samuel and Aremu, Anuoluwapo and Ogayo, Perez and Neubig, Graham},
      year = {2023},
      journal = {arXiv preprint arXiv:2305.16171},
      booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023, Toronto, Canada, 9-14 July 2023},
      publisher = {Association for Computational Linguistics},
      series = {Findings of {ACL}},
      volume = {{ACL} 2023},
    }

11. Multilingual Large Language Models Are Not (Yet) Code-Switchers

    Ruochen Zhang,  Samuel Cahyawijaya, Jan Christian Blaise Cruz, and Alham Fikri Aji.

    arXiv preprint arXiv:2305.14235. 2023.

    arXiv Bib

    @article{zhang2023multilingual,
      title = {{Multilingual Large Language Models Are Not (Yet) Code-Switchers}},
      author = {Zhang, Ruochen and Cahyawijaya, Samuel and Cruz, Jan Christian Blaise and Aji, Alham Fikri},
      year = {2023},
      journal = {arXiv preprint arXiv:2305.14235},
    }

12. NusaCrowd: Open Source Initiative for Indonesian NLP Resources

    Samuel Cahyawijaya, Holy Lovenia, Alham Fikri Aji, Genta Indra Winata, Bryan Wilie, Rahmad Mahendra, Christian Wibisono, Ade Romadhony, Karissa Vincentio, Fajri Koto, and others.

    In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, 9-14 July 2023. 2023.

    arXiv Bib

    @inproceedings{cahyawijaya2022nusacrowd,
      title = {{NusaCrowd: Open Source Initiative for Indonesian NLP Resources}},
      author = {Cahyawijaya, Samuel and Lovenia, Holy and Aji, Alham Fikri and Winata, Genta Indra and Wilie, Bryan and Mahendra, Rahmad and Wibisono, Christian and Romadhony, Ade and Vincentio, Karissa and Koto, Fajri and others},
      year = {2023},
      journal = {arXiv preprint arXiv:2207.10524},
      booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023, Toronto, Canada, 9-14 July 2023},
      publisher = {Association for Computational Linguistics},
      series = {Findings of {ACL}},
      volume = {{ACL} 2023},
    }

13. NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages

    Genta Indra Winata, Alham Fikri Aji,  Samuel Cahyawijaya, Rahmad Mahendra, Fajri Koto, Ade Romadhony, Kemal Kurniawan, David Moeljadi, Radityo Eko Prasojo, Pascale Fung, Timothy Baldwin, Jey Han Lau, Rico Sennrich, and Sebastian Ruder.

    In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. May 2023.

    Bib PDF

    @inproceedings{winata-etal-2023-nusax,
      title = {{NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages}},
      author = {Winata, Genta Indra and Aji, Alham Fikri and Cahyawijaya, Samuel and Mahendra, Rahmad and Koto, Fajri and Romadhony, Ade and Kurniawan, Kemal and Moeljadi, David and Prasojo, Radityo Eko and Fung, Pascale and Baldwin, Timothy and Lau, Jey Han and Sennrich, Rico and Ruder, Sebastian},
      year = {2023},
      month = may,
      booktitle = {Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics},
      publisher = {Association for Computational Linguistics},
      address = {Dubrovnik, Croatia},
      pages = {815--834},
    }

14. Prompting Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages

    Zheng-Xin Yong, Ruochen Zhang, Jessica Zosa Forde, Skyler Wang,  Samuel Cahyawijaya, Holy Lovenia, Lintang Sutawika, Jan Christian Blaise Cruz, Long Phan, Yin Lin Tan, and others.

    arXiv preprint arXiv:2303.13592. May 2023.

    arXiv Bib

    @article{yong2023prompting,
      title = {{Prompting Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages}},
      author = {Yong, Zheng-Xin and Zhang, Ruochen and Forde, Jessica Zosa and Wang, Skyler and Cahyawijaya, Samuel and Lovenia, Holy and Sutawika, Lintang and Cruz, Jan Christian Blaise and Phan, Long and Tan, Yin Lin and others},
      year = {2023},
      journal = {arXiv preprint arXiv:2303.13592},
    }

15. The Obscure Limitation of Modular Multilingual Language Models

    Muhammad Farid Adilazuarda,  Samuel Cahyawijaya, and Ayu Purwarianti.

    In Tiny Papers of Eleventh International Conference on Learning Representations (ICLR), Kigali, Rwanda, 5 May 2023. May 2023.

    Bib PDF

    @inproceedings{adilazuarda2023obscure,
      title = {{The Obscure Limitation of Modular Multilingual Language Models}},
      author = {Adilazuarda, Muhammad Farid and Cahyawijaya, Samuel and Purwarianti, Ayu},
      year = {2023},
      booktitle = {Tiny Papers of Eleventh International Conference on Learning Representations (ICLR), Kigali, Rwanda, 5 May 2023},
      publisher = {ICLR},
    }

16. Towards Answering Open-ended Ethical Quandary Questions

    Yejin Bang, Nayeon Lee, Tiezheng Yu, Leila Khalatbari, Yan Xu,  Samuel Cahyawijaya, Dan Su, Bryan Wilie, Romain Barraud, Elham J Barezi, and others.

    In Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 20223, The Workshop on Artificial Intelligence for Social Good, AI4SG 2023, Washington DC, USA, February 14, 2023. May 2023.

    arXiv Bib

    @inproceedings{bang2022towards,
      title = {{Towards Answering Open-ended Ethical Quandary Questions}},
      author = {Bang, Yejin and Lee, Nayeon and Yu, Tiezheng and Khalatbari, Leila and Xu, Yan and Cahyawijaya, Samuel and Su, Dan and Wilie, Bryan and Barraud, Romain and Barezi, Elham J and others},
      year = {2023},
      booktitle = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence, {AAAI} 20223, The Workshop on Artificial Intelligence for Social Good, {AI4SG} 2023, Washington DC, USA, February 14, 2023},
    }

17. Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue

    Holy Lovenia,  Samuel Cahyawijaya, and Pascale Fung.

    In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop. May 2023.

    Bib PDF

    @inproceedings{lovenia-etal-2023-one,
      title = {{Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue}},
      author = {Lovenia, Holy and Cahyawijaya, Samuel and Fung, Pascale},
      year = {2023},
      month = may,
      booktitle = {Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop},
      publisher = {Association for Computational Linguistics},
      address = {Dubrovnik, Croatia},
      pages = {61--72},
    }

2022

1. ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation

   Holy Lovenia,  Samuel Cahyawijaya, Genta Indra Winata, Peng Xu, Yan Xu, Zihan Liu, Rita Frieske, Tiezheng Yu, Wenliang Dai, Elham J. Barezi, Qifeng Chen, Xiaojuan Ma, Bertram E. Shi, and Pascale Fung.

   In Proceedings of the Thirteenth Language Resources and Evaluation Conference, LREC 2022, Marseille, France, 20-25 June 2022. May 2022.

   arXiv Bib PDF

   @inproceedings{DBLP:conf/lrec/LoveniaCW00LFYD22,
     title = {{ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation}},
     author = {Lovenia, Holy and Cahyawijaya, Samuel and Winata, Genta Indra and Xu, Peng and Xu, Yan and Liu, Zihan and Frieske, Rita and Yu, Tiezheng and Dai, Wenliang and Barezi, Elham J. and Chen, Qifeng and Ma, Xiaojuan and Shi, Bertram E. and Fung, Pascale},
     year = {2022},
     journal = {CoRR},
     booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference, {LREC} 2022, Marseille, France, 20-25 June 2022},
     publisher = {European Language Resources Association},
     volume = {abs/2112.06223},
     pages = {7259--7268},
     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},
     timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
     biburl = {https://dblp.org/rec/conf/lrec/LoveniaCW00LFYD22.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

2. Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset

   Tiezheng Yu, Rita Frieske, Peng Xu,  Samuel Cahyawijaya, Cheuk Tung Shadow Yiu, Holy Lovenia, Wenliang Dai, Elham J. Barezi, Qifeng Chen, Xiaojuan Ma, Bertram E. Shi, and Pascale Fung.

   In Proceedings of the Thirteenth Language Resources and Evaluation Conference, LREC 2022, Marseille, France, 20-25 June 2022. May 2022.

   Bib PDF

   @inproceedings{DBLP:conf/lrec/YuF0CYLDBCMSF22,
     title = {{Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset}},
     author = {Yu, Tiezheng and Frieske, Rita and Xu, Peng and Cahyawijaya, Samuel and Yiu, Cheuk Tung Shadow and Lovenia, Holy and Dai, Wenliang and Barezi, Elham J. and Chen, Qifeng and Ma, Xiaojuan and Shi, Bertram E. and Fung, Pascale},
     year = {2022},
     booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference, {LREC} 2022, Marseille, France, 20-25 June 2022},
     publisher = {European Language Resources Association},
     pages = {6487--6494},
     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},
     timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
     biburl = {https://dblp.org/rec/conf/lrec/YuF0CYLDBCMSF22.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

3. BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing

   Jason Fries, Leon Weber, Natasha Seelam, Gabriel Altay, Debajyoti Datta, Samuele Garda, Sunny Kang, Rosaline Su, Wojciech Kusa,  Samuel Cahyawijaya, and others.

   In Advances in Neural Information Processing Systems. May 2022.

   Bib PDF

   @inproceedings{fries2022bigbio,
     title = {{BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing}},
     author = {Fries, Jason and Weber, Leon and Seelam, Natasha and Altay, Gabriel and Datta, Debajyoti and Garda, Samuele and Kang, Sunny and Su, Rosaline and Kusa, Wojciech and Cahyawijaya, Samuel and others},
     year = {2022},
     booktitle = {Advances in Neural Information Processing Systems},
     volume = {35},
     pages = {25792--25806},
   }

4. Bloom: A 176b-parameter open-access multilingual language model

   Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, and others.

   In arXiv preprint arXiv:2211.05100. May 2022.

   arXiv Bib

   @inproceedings{scao2022bloom,
     title = {{Bloom: A 176b-parameter open-access multilingual language model}},
     author = {Scao, Teven Le and Fan, Angela and Akiki, Christopher and Pavlick, Ellie and Ili{\'c}, Suzana and Hesslow, Daniel and Castagn{\'e}, Roman and Luccioni, Alexandra Sasha and Yvon, Fran{\c{c}}ois and Gall{\'e}, Matthias and others},
     year = {2022},
     journal = {arXiv},
     booktitle = {arXiv preprint arXiv:2211.05100},
   }

5. Can Question Rewriting Help Conversational Question Answering?

   Etsuko Ishii, Yan Xu,  Samuel Cahyawijaya, and Bryan Wilie.

   In Proceedings of the Third Workshop on Insights from Negative Results in NLP, Insights@ACL 2022, Dublin, Ireland, May 26, 2022. May 2022.

   arXiv Bib PDF

   @inproceedings{DBLP:conf/acl-insights/IshiiXCW22,
     title = {{Can Question Rewriting Help Conversational Question Answering?}},
     author = {Ishii, Etsuko and Xu, Yan and Cahyawijaya, Samuel and Wilie, Bryan},
     year = {2022},
     journal = {CoRR},
     booktitle = {Proceedings of the Third Workshop on Insights from Negative Results in NLP, Insights@ACL 2022, Dublin, Ireland, May 26, 2022},
     publisher = {Association for Computational Linguistics},
     volume = {abs/2204.06239},
     pages = {94--99},
     doi = {10.18653/v1/2022.insights-1.13},
     editor = {Tafreshi, Shabnam and Sedoc, Jo{\~{a}}o and Rogers, Anna and Drozd, Aleksandr and Rumshisky, Anna and Akula, Arjun R.},
     timestamp = {Mon, 01 Aug 2022 01:00:00 +0200},
     biburl = {https://dblp.org/rec/conf/acl-insights/IshiiXCW22.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

6. CI-AVSR: A Cantonese Audio-Visual Speech Datasetfor In-car Command Recognition

   Wenliang Dai,  Samuel Cahyawijaya, Tiezheng Yu, Elham J. Barezi, Peng Xu, Cheuk Tung Yiu, Rita Frieske, Holy Lovenia, Genta Indra Winata, Qifeng Chen, Xiaojuan Ma, Bertram E. Shi, and Pascale Fung.

   In Proceedings of the Thirteenth Language Resources and Evaluation Conference, LREC 2022, Marseille, France, 20-25 June 2022. May 2022.

   arXiv Bib PDF

   @inproceedings{DBLP:conf/lrec/DaiCYB0YFLWCMSF22,
     title = {{CI-AVSR: A Cantonese Audio-Visual Speech Datasetfor In-car Command Recognition}},
     author = {Dai, Wenliang and Cahyawijaya, Samuel and Yu, Tiezheng and Barezi, Elham J. and Xu, Peng and Yiu, Cheuk Tung and Frieske, Rita and Lovenia, Holy and Winata, Genta Indra and Chen, Qifeng and Ma, Xiaojuan and Shi, Bertram E. and Fung, Pascale},
     year = {2022},
     journal = {CoRR},
     booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference, {LREC} 2022, Marseille, France, 20-25 June 2022},
     publisher = {European Language Resources Association},
     volume = {abs/2201.03804},
     pages = {6786--6793},
     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},
     timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
     biburl = {https://dblp.org/rec/conf/lrec/DaiCYB0YFLWCMSF22.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

7. Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension

   Holy Lovenia, Bryan Wilie, Willy Chung, Min Zeng,  Samuel Cahyawijaya, Su Dan, and Pascale Fung.

   In Proceedings of the 7th Workshop on Representation Learning for NLP, RepL4NLP@ACL 2022, Dublin, Ireland, May 26, 2022. May 2022.

   arXiv Bib PDF

   @inproceedings{DBLP:conf/rep4nlp/LoveniaWCZCDF22,
     title = {{Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension}},
     author = {Lovenia, Holy and Wilie, Bryan and Chung, Willy and Zeng, Min and Cahyawijaya, Samuel and Dan, Su and Fung, Pascale},
     year = {2022},
     journal = {CoRR},
     booktitle = {Proceedings of the 7th Workshop on Representation Learning for NLP, RepL4NLP@ACL 2022, Dublin, Ireland, May 26, 2022},
     publisher = {Association for Computational Linguistics},
     volume = {abs/2203.16027},
     pages = {60--66},
     doi = {10.18653/v1/2022.repl4nlp-1.7},
     editor = {Gella, Spandana and He, He and Majumder, Bodhisattwa Prasad and Can, Burcu and Giunchiglia, Eleonora and Cahyawijaya, Samuel and Min, Sewon and Mozes, Maximilian and Li, Xiang Lorraine and Augenstein, Isabelle and Rogers, Anna and Cho, Kyunghyun and Grefenstette, Edward and Rimell, Laura and Dyer, Chris},
     timestamp = {Mon, 01 Aug 2022 01:00:00 +0200},
     biburl = {https://dblp.org/rec/conf/rep4nlp/LoveniaWCZCDF22.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

8. Every picture tells a story: Image-grounded controllable stylistic story generation

   Holy Lovenia, Bryan Wilie, Romain Barraud,  Samuel Cahyawijaya, Willy Chung, and Pascale Fung.

   In Proceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature. Oct 2022.

   Bib PDF

   @inproceedings{lovenia-etal-2022-every,
     title = {{Every picture tells a story: Image-grounded controllable stylistic story generation}},
     author = {Lovenia, Holy and Wilie, Bryan and Barraud, Romain and Cahyawijaya, Samuel and Chung, Willy and Fung, Pascale},
     year = {2022},
     month = oct,
     booktitle = {Proceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature},
     publisher = {International Conference on Computational Linguistics},
     address = {Gyeongju, Republic of Korea},
     pages = {40--52},
   }

9. GEMv2: Multilingual NLG Benchmarking in a Single Line of Code

   Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, and Bernd Bohnet.

   In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Dec 2022.

   Bib PDF

   @inproceedings{gehrmann-etal-2022-gemv2,
     title = {{GEMv2: Multilingual NLG Benchmarking in a Single Line of Code}},
     author = {Gehrmann, Sebastian and Bhattacharjee, Abhik and Mahendiran, Abinaya and Wang, Alex and Papangelis, Alexandros and Madaan, Aman and Mcmillan-major, Angelina and Shvets, Anna and Upadhyay, Ashish and Bohnet, Bernd},
     year = {2022},
     month = dec,
     booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations},
     publisher = {Association for Computational Linguistics},
     address = {Abu Dhabi, UAE},
     pages = {266--281},
   }

10. How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling

    Samuel Cahyawijaya, Bryan Wilie, Holy Lovenia, Huan Zhong, MingQian Zhong, Yuk-Yu Nancy Ip, and Pascale Fung.

    In Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI). Dec 2022.

    Bib PDF

    @inproceedings{cahyawijaya-etal-2022-long,
      title = {{How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling}},
      author = {Cahyawijaya, Samuel and Wilie, Bryan and Lovenia, Holy and Zhong, Huan and Zhong, MingQian and Ip, Yuk-Yu Nancy and Fung, Pascale},
      year = {2022},
      month = dec,
      booktitle = {Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis (LOUHI)},
      publisher = {Association for Computational Linguistics},
      address = {Abu Dhabi, United Arab Emirates (Hybrid)},
      pages = {160--172},
    }

11. IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages

    Muhammad Farid Adilazuarda,  Samuel Cahyawijaya, Genta Indra Winata, Pascale Fung, and Ayu Purwarianti.

    In Proceedings of the First Workshop on Scaling Up Multilingual Evaluation. Nov 2022.

    Bib PDF

    @inproceedings{adilazuarda-etal-2022-indorobusta,
      title = {{IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages}},
      author = {Adilazuarda, Muhammad Farid and Cahyawijaya, Samuel and Winata, Genta Indra and Fung, Pascale and Purwarianti, Ayu},
      year = {2022},
      month = nov,
      booktitle = {Proceedings of the First Workshop on Scaling Up Multilingual Evaluation},
      publisher = {Association for Computational Linguistics},
      address = {Online},
      pages = {25--34},
    }

12. Integrating Question Rewrites in Conversational Question Answering: A Reinforcement Learning Approach

    Etsuko Ishii, Bryan Wilie, Yan Xu,  Samuel Cahyawijaya, and Pascale Fung.

    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, ACL 2022, Dublin, Ireland, May 22-27, 2022. Nov 2022.

    Bib PDF

    @inproceedings{DBLP:conf/acl/IshiiW0CF22,
      title = {{Integrating Question Rewrites in Conversational Question Answering: A Reinforcement Learning Approach}},
      author = {Ishii, Etsuko and Wilie, Bryan and Xu, Yan and Cahyawijaya, Samuel and Fung, Pascale},
      year = {2022},
      booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, {ACL} 2022, Dublin, Ireland, May 22-27, 2022},
      publisher = {Association for Computational Linguistics},
      pages = {55--66},
      doi = {10.18653/v1/2022.acl-srw.6},
      editor = {Louvan, Samuel and Madotto, Andrea and Madureira, Brielen},
      timestamp = {Mon, 01 Aug 2022 01:00:00 +0200},
      biburl = {https://dblp.org/rec/conf/acl/IshiiW0CF22.bib},
      bibsource = {dblp computer science bibliography, https://dblp.org},
    }

13. Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands

    Wenliang Dai,  Samuel Cahyawijaya, Tiezheng Yu, Elham J. Barezi, and Pascale Fung.

    CoRR. Nov 2022.

    arXiv Bib PDF

    @article{DBLP:journals/corr/abs-2207-02663,
      title = {{Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands}},
      author = {Dai, Wenliang and Cahyawijaya, Samuel and Yu, Tiezheng and Barezi, Elham J. and Fung, Pascale},
      year = {2022},
      journal = {CoRR},
      volume = {abs/2207.02663},
      doi = {10.48550/arXiv.2207.02663},
      eprinttype = {arXiv},
      timestamp = {Wed, 13 Jul 2022 01:00:00 +0200},
      biburl = {https://dblp.org/rec/journals/corr/abs-2207-02663.bib},
      bibsource = {dblp computer science bibliography, https://dblp.org},
    }

14. One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia

    Alham Fikri Aji, Genta Indra Winata, Fajri Koto,  Samuel Cahyawijaya, Ade Romadhony, Rahmad Mahendra, Kemal Kurniawan, David Moeljadi, Radityo Eko Prasojo, Timothy Baldwin, Jey Han Lau, and Sebastian Ruder.

    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022. Nov 2022.

    arXiv Bib PDF

    @inproceedings{DBLP:conf/acl/AjiWKCRMKMPBLR22,
      title = {{One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia}},
      author = {Aji, Alham Fikri and Winata, Genta Indra and Koto, Fajri and Cahyawijaya, Samuel and Romadhony, Ade and Mahendra, Rahmad and Kurniawan, Kemal and Moeljadi, David and Prasojo, Radityo Eko and Baldwin, Timothy and Lau, Jey Han and Ruder, Sebastian},
      year = {2022},
      journal = {CoRR},
      booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), {ACL} 2022, Dublin, Ireland, May 22-27, 2022},
      publisher = {Association for Computational Linguistics},
      volume = {abs/2203.13357},
      pages = {7226--7249},
      doi = {10.18653/v1/2022.acl-long.500},
      editor = {Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline},
      timestamp = {Mon, 01 Aug 2022 01:00:00 +0200},
      biburl = {https://dblp.org/rec/conf/acl/AjiWKCRMKMPBLR22.bib},
      bibsource = {dblp computer science bibliography, https://dblp.org},
      eprinttype = {arXiv},
    }

15. Proceedings of the 7th Workshop on Representation Learning for NLP, RepL4NLP@ACL 2022, Dublin, Ireland, May 26, 2022

    . Nov 2022.

    Bib PDF

    @proceedings{DBLP:conf/rep4nlp/2022,
      title = {{Proceedings of the 7th Workshop on Representation Learning for NLP, RepL4NLP@ACL 2022, Dublin, Ireland, May 26, 2022}},
      year = {2022},
      publisher = {Association for Computational Linguistics},
      isbn = {978-1-955917-48-3},
      editor = {Gella, Spandana and He, He and Majumder, Bodhisattwa Prasad and Can, Burcu and Giunchiglia, Eleonora and Cahyawijaya, Samuel and Min, Sewon and Mozes, Maximilian and Li, Xiang Lorraine and Augenstein, Isabelle and Rogers, Anna and Cho, Kyunghyun and Grefenstette, Edward and Rimell, Laura and Dyer, Chris},
      timestamp = {Mon, 30 May 2022 01:00:00 +0200},
      biburl = {https://dblp.org/rec/conf/rep4nlp/2022.bib},
      bibsource = {dblp computer science bibliography, https://dblp.org},
    }

16. Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters

    Yan Xu, Etsuko Ishii,  Samuel Cahyawijaya, Zihan Liu, Genta Indra Winata, Andrea Madotto, Dan Su, and Pascale Fung.

    In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, DialDoc@ACL 2022, Dublin, Ireland, May 26, 2022. Nov 2022.

    Bib PDF

    @inproceedings{DBLP:conf/acl-dialdoc/XuICLWMSF22,
      title = {{Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters}},
      author = {Xu, Yan and Ishii, Etsuko and Cahyawijaya, Samuel and Liu, Zihan and Winata, Genta Indra and Madotto, Andrea and Su, Dan and Fung, Pascale},
      year = {2022},
      booktitle = {Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, DialDoc@ACL 2022, Dublin, Ireland, May 26, 2022},
      publisher = {Association for Computational Linguistics},
      pages = {93--107},
      doi = {10.18653/v1/2022.dialdoc-1.10},
      editor = {Feng, Song and Wan, Hui and Yuan, Caixia and Yu, Han},
      timestamp = {Fri, 04 Nov 2022 09:06:28 +0100},
      biburl = {https://dblp.org/rec/conf/acl-dialdoc/XuICLWMSF22.bib},
      bibsource = {dblp computer science bibliography, https://dblp.org},
    }

17. SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study

    Samuel Cahyawijaya, Tiezheng Yu, Zihan Liu, Xiaopu Zhou, Tze Wing Tiffany Mak, Nancy Y. Ip, and Pascale Fung.

    In Proceedings of the 21st Workshop on Biomedical Language Processing, BioNLP@ACL 2022, Dublin, Ireland, May 26, 2022. Nov 2022.

    arXiv Bib PDF

    @inproceedings{DBLP:conf/bionlp/CahyawijayaYLZM22,
      title = {{SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study}},
      author = {Cahyawijaya, Samuel and Yu, Tiezheng and Liu, Zihan and Zhou, Xiaopu and Mak, Tze Wing Tiffany and Ip, Nancy Y. and Fung, Pascale},
      year = {2022},
      journal = {CoRR},
      booktitle = {Proceedings of the 21st Workshop on Biomedical Language Processing, BioNLP@ACL 2022, Dublin, Ireland, May 26, 2022},
      publisher = {Association for Computational Linguistics},
      volume = {abs/2204.06699},
      pages = {140--154},
      doi = {10.18653/v1/2022.bionlp-1.14},
      editor = {Demner{-}Fushman, Dina and Cohen, Kevin Bretonnel and Ananiadou, Sophia and Tsujii, Junichi},
      timestamp = {Mon, 01 Aug 2022 01:00:00 +0200},
      biburl = {https://dblp.org/rec/conf/bionlp/CahyawijayaYLZM22.bib},
      bibsource = {dblp computer science bibliography, https://dblp.org},
      eprinttype = {arXiv},
    }

18. VScript: Controllable Script Generation with Visual Presentation

    Ziwei Ji, Yan Xu, I-Tsun Cheng,  Samuel Cahyawijaya, Rita Frieske, Etsuko Ishii, Min Zeng, Andrea Madotto, and Pascale Fung.

    In 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: System Demonstrations. Nov 2022.

    Bib PDF

    @inproceedings{ji-etal-2022-vscript,
      title = {{VScript: Controllable Script Generation with Visual Presentation}},
      author = {Ji, Ziwei and Xu, Yan and Cheng, I-Tsun and Cahyawijaya, Samuel and Frieske, Rita and Ishii, Etsuko and Zeng, Min and Madotto, Andrea and Fung, Pascale},
      year = {2022},
      month = nov,
      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: System Demonstrations},
      publisher = {Association for Computational Linguistics},
      address = {Taipei, Taiwan},
      pages = {1--8},
    }

2021

1. Are Multilingual Models Effective in Code-Switching?

   Genta Indra Winata,  Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin, Andrea Madotto, and Pascale Fung.

   In Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching, CALCS@NAACL 2021, Online, June 11, 2021. Nov 2021.

   arXiv Bib PDF

     title = {{Are Multilingual Models Effective in Code-Switching?}},
     author = {Winata, Genta Indra and Cahyawijaya, Samuel and Liu, Zihan and Lin, Zhaojiang and Madotto, Andrea and Fung, Pascale},
     year = {2021},
     journal = {CoRR},
     booktitle = {Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching, CALCS@NAACL 2021, Online, June 11, 2021},
     publisher = {Association for Computational Linguistics},
     volume = {abs/2103.13309},
     pages = {142--153},
     doi = {10.18653/v1/2021.calcs-1.20},
     editor = {Solorio, Thamar and Chen, Shuguang and Black, Alan W. and Diab, Mona T. and Sitaram, Sunayana and Soto, Victor and Yilmaz, Emre and Srinivasan, Anirudh},
     timestamp = {Fri, 11 Nov 2022 16:40:02 +0100},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

2. CrossNER: Evaluating Cross-Domain Named Entity Recognition

   Zihan Liu, Yan Xu, Tiezheng Yu, Wenliang Dai, Ziwei Ji,  Samuel Cahyawijaya, Andrea Madotto, and Pascale Fung.

   In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021. Nov 2021.

   arXiv Bib PDF

   @inproceedings{DBLP:conf/aaai/Liu0YDJCMF21,
     title = {{CrossNER: Evaluating Cross-Domain Named Entity Recognition}},
     author = {Liu, Zihan and Xu, Yan and Yu, Tiezheng and Dai, Wenliang and Ji, Ziwei and Cahyawijaya, Samuel and Madotto, Andrea and Fung, Pascale},
     year = {2021},
     journal = {CoRR},
     booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9, 2021},
     publisher = {{AAAI} Press},
     volume = {abs/2012.04373},
     pages = {13452--13460},
     timestamp = {Mon, 07 Jun 2021 01:00:00 +0200},
     biburl = {https://dblp.org/rec/conf/aaai/Liu0YDJCMF21.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

3. ERICA: An Empathetic Android Companion for Covid-19 Quarantine

   Etsuko Ishii, Genta Indra Winata,  Samuel Cahyawijaya, Divesh Lala, Tatsuya Kawahara, and Pascale Fung.

   In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGdial 2021, Singapore and Online, July 29-31, 2021. Nov 2021.

   arXiv Bib PDF

   @inproceedings{DBLP:conf/sigdial/IshiiWCLKF21,
     title = {{ERICA: An Empathetic Android Companion for Covid-19 Quarantine}},
     author = {Ishii, Etsuko and Winata, Genta Indra and Cahyawijaya, Samuel and Lala, Divesh and Kawahara, Tatsuya and Fung, Pascale},
     year = {2021},
     journal = {CoRR},
     booktitle = {Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGdial 2021, Singapore and Online, July 29-31, 2021},
     publisher = {Association for Computational Linguistics},
     volume = {abs/2106.02325},
     pages = {257--260},
     editor = {Li, Haizhou and Levow, Gina{-}Anne and Yu, Zhou and Gupta, Chitralekha and Sisman, Berrak and Cai, Siqi and Vandyke, David and Dethlefs, Nina and Wu, Yan and Li, Junyi Jessy},
     timestamp = {Wed, 25 Aug 2021 17:11:16 +0200},
     biburl = {https://dblp.org/rec/conf/sigdial/IshiiWCLKF21.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

4. Greenformer: Factorization Toolkit for Efficient Deep Neural Networks

   Samuel Cahyawijaya, Genta Indra Winata, Holy Lovenia, Bryan Wilie, Wenliang Dai, Etsuko Ishii, and Pascale Fung.

   CoRR. Nov 2021.

   arXiv Bib

   @article{DBLP:journals/corr/abs-2109-06762,
     title = {{Greenformer: Factorization Toolkit for Efficient Deep Neural Networks}},
     author = {Cahyawijaya, Samuel and Winata, Genta Indra and Lovenia, Holy and Wilie, Bryan and Dai, Wenliang and Ishii, Etsuko and Fung, Pascale},
     year = {2021},
     journal = {CoRR},
     volume = {abs/2109.06762},
     eprinttype = {arXiv},
     timestamp = {Tue, 21 Sep 2021 01:00:00 +0200},
     biburl = {https://dblp.org/rec/journals/corr/abs-2109-06762.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

5. Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation

   Samuel Cahyawijaya.

   CoRR. Nov 2021.

   arXiv Bib

   @article{DBLP:journals/corr/abs-2108-10808,
     title = {{Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation}},
     author = {Cahyawijaya, Samuel},
     year = {2021},
     journal = {CoRR},
     volume = {abs/2108.10808},
     eprinttype = {arXiv},
     timestamp = {Fri, 27 Aug 2021 01:00:00 +0200},
     biburl = {https://dblp.org/rec/journals/corr/abs-2108-10808.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

6. IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation

   Samuel Cahyawijaya, Genta Indra Winata, Bryan Wilie, Karissa Vincentio, Xiaohong Li, Adhiguna Kuncoro, Sebastian Ruder, Zhi Yuan Lim, Syafri Bahar, Masayu Leylia Khodra, Ayu Purwarianti, and Pascale Fung.

   In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021. Nov 2021.

   arXiv Bib PDF

   @inproceedings{DBLP:conf/emnlp/CahyawijayaWWVL21,
     title = {{IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation}},
     author = {Cahyawijaya, Samuel and Winata, Genta Indra and Wilie, Bryan and Vincentio, Karissa and Li, Xiaohong and Kuncoro, Adhiguna and Ruder, Sebastian and Lim, Zhi Yuan and Bahar, Syafri and Khodra, Masayu Leylia and Purwarianti, Ayu and Fung, Pascale},
     year = {2021},
     journal = {CoRR},
     booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021},
     publisher = {Association for Computational Linguistics},
     volume = {abs/2104.08200},
     pages = {8875--8898},
     doi = {10.18653/v1/2021.emnlp-main.699},
     editor = {Moens, Marie{-}Francine and Huang, Xuanjing and Specia, Lucia and Yih, Scott Wen{-}tau},
     timestamp = {Thu, 20 Jan 2022 00:00:00 +0100},
     biburl = {https://dblp.org/rec/conf/emnlp/CahyawijayaWWVL21.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

7. Model Generalization on COVID-19 Fake News Detection

   Yejin Bang, Etsuko Ishii,  Samuel Cahyawijaya, Ziwei Ji, and Pascale Fung.

   In Combating Online Hostile Posts in Regional Languages during Emergency Situation - First International Workshop, CONSTRAINT 2021, Collocated with AAAI 2021, Virtual Event, February 8, 2021, Revised Selected Papers. Nov 2021.

   arXiv Bib PDF

   @inproceedings{DBLP:conf/aaai/BangICJF21,
     title = {{Model Generalization on COVID-19 Fake News Detection}},
     author = {Bang, Yejin and Ishii, Etsuko and Cahyawijaya, Samuel and Ji, Ziwei and Fung, Pascale},
     year = {2021},
     journal = {CoRR},
     booktitle = {Combating Online Hostile Posts in Regional Languages during Emergency Situation - First International Workshop, {CONSTRAINT} 2021, Collocated with {AAAI} 2021, Virtual Event, February 8, 2021, Revised Selected Papers},
     publisher = {Springer},
     series = {Communications in Computer and Information Science},
     volume = {1402},
     pages = {128--140},
     doi = {10.1007/978-3-030-73696-5\_13},
     editor = {Chakraborty, Tanmoy and Shu, Kai and Bernard, H. Russell and Liu, Huan and Akhtar, Md. Shad},
     timestamp = {Tue, 17 Aug 2021 16:18:44 +0200},
     biburl = {https://dblp.org/rec/conf/aaai/BangICJF21.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

8. Multimodal End-to-End Sparse Model for Emotion Recognition

   Wenliang Dai,  Samuel Cahyawijaya, Zihan Liu, and Pascale Fung.

   In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021. Nov 2021.

   arXiv Bib PDF

   @inproceedings{DBLP:conf/naacl/DaiCLF21,
     title = {{Multimodal End-to-End Sparse Model for Emotion Recognition}},
     author = {Dai, Wenliang and Cahyawijaya, Samuel and Liu, Zihan and Fung, Pascale},
     year = {2021},
     journal = {CoRR},
     booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, {NAACL-HLT} 2021, Online, June 6-11, 2021},
     publisher = {Association for Computational Linguistics},
     volume = {abs/2103.09666},
     pages = {5305--5316},
     doi = {10.18653/v1/2021.naacl-main.417},
     editor = {Toutanova, Kristina and Rumshisky, Anna and Zettlemoyer, Luke and Hakkani{-}T{\"{u}}r, Dilek and Beltagy, Iz and Bethard, Steven and Cotterell, Ryan and Chakraborty, Tanmoy and Zhou, Yichao},
     timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
     biburl = {https://dblp.org/rec/conf/naacl/DaiCLF21.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     eprinttype = {arXiv},
   }

9. NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation

   Kaustubh D. Dhole, Varun Gangal, Sebastian Gehrmann, Aadesh Gupta, Zhenhao Li, Saad Mahamood, Abinaya Mahendiran, Simon Mille, Ashish Srivastava, Samson Tan, Tongshuang Wu, Jascha Sohl-Dickstein, Jinho D. Choi, Eduard H. Hovy, Ondrej Dusek, Sebastian Ruder, Sajant Anand, Nagender Aneja, Rabin Banjade, Lisa Barthe, Hanna Behnke, Ian Berlot-Attwell, Connor Boyle, Caroline Brun, Marco Antonio Sobrevilla Cabezudo,  Samuel Cahyawijaya, Emile Chapuis, Wanxiang Che, Mukund Choudhary, Christian Clauss, Pierre Colombo, Filip Cornell, Gautier Dagan, Mayukh Das, Tanay Dixit, Thomas Dopierre, Paul-Alexis Dray, Suchitra Dubey, Tatiana Ekeinhor, Marco Di Giovanni, Rishabh Gupta, Rishabh Gupta, Louanes Hamla, Sang Han, Fabrice Harel-Canada, Antoine Honore, Ishan Jindal, Przemyslaw K. Joniak, Denis Kleyko, Venelin Kovatchev, and al..

   CoRR. Nov 2021.

   arXiv Bib

   @article{DBLP:journals/corr/abs-2112-02721,
     title = {{NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation}},
     author = {Dhole, Kaustubh D. and Gangal, Varun and Gehrmann, Sebastian and Gupta, Aadesh and Li, Zhenhao and Mahamood, Saad and Mahendiran, Abinaya and Mille, Simon and Srivastava, Ashish and Tan, Samson and Wu, Tongshuang and Sohl{-}Dickstein, Jascha and Choi, Jinho D. and Hovy, Eduard H. and Dusek, Ondrej and Ruder, Sebastian and Anand, Sajant and Aneja, Nagender and Banjade, Rabin and Barthe, Lisa and Behnke, Hanna and Berlot{-}Attwell, Ian and Boyle, Connor and Brun, Caroline and Cabezudo, Marco Antonio Sobrevilla and Cahyawijaya, Samuel and Chapuis, Emile and Che, Wanxiang and Choudhary, Mukund and Clauss, Christian and Colombo, Pierre and Cornell, Filip and Dagan, Gautier and Das, Mayukh and Dixit, Tanay and Dopierre, Thomas and Dray, Paul{-}Alexis and Dubey, Suchitra and Ekeinhor, Tatiana and Giovanni, Marco Di and Gupta, Rishabh and Gupta, Rishabh and Hamla, Louanes and Han, Sang and Harel{-}Canada, Fabrice and Honore, Antoine and Jindal, Ishan and Joniak, Przemyslaw K. and Kleyko, Denis and Kovatchev, Venelin and et al.},
     year = {2021},
     journal = {CoRR},
     volume = {abs/2112.02721},
     eprinttype = {arXiv},
     timestamp = {Wed, 08 Dec 2021 00:00:00 +0100},
     biburl = {https://dblp.org/rec/journals/corr/abs-2112-02721.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
   }

10. On the Importance of Word Order Information in Cross-lingual Sequence Labeling

    Zihan Liu, Genta Indra Winata,  Samuel Cahyawijaya, Andrea Madotto, Zhaojiang Lin, and Pascale Fung.

    In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021. Nov 2021.

    Bib PDF

    @inproceedings{DBLP:conf/aaai/LiuWCMLF21,
      title = {{On the Importance of Word Order Information in Cross-lingual Sequence Labeling}},
      author = {Liu, Zihan and Winata, Genta Indra and Cahyawijaya, Samuel and Madotto, Andrea and Lin, Zhaojiang and Fung, Pascale},
      year = {2021},
      booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9, 2021},
      publisher = {{AAAI} Press},
      pages = {13461--13469},
      timestamp = {Mon, 07 Jun 2021 01:00:00 +0200},
      biburl = {https://dblp.org/rec/conf/aaai/LiuWCMLF21.bib},
      bibsource = {dblp computer science bibliography, https://dblp.org},
    }

11. Weakly-supervised Multi-task Learning for Multimodal Affect Recognition

    Wenliang Dai,  Samuel Cahyawijaya, Yejin Bang, and Pascale Fung.

    CoRR. Nov 2021.

    arXiv Bib

    @article{DBLP:journals/corr/abs-2104-11560,
      title = {{Weakly-supervised Multi-task Learning for Multimodal Affect Recognition}},
      author = {Dai, Wenliang and Cahyawijaya, Samuel and Bang, Yejin and Fung, Pascale},
      year = {2021},
      journal = {CoRR},
      volume = {abs/2104.11560},
      eprinttype = {arXiv},
      timestamp = {Tue, 27 Apr 2021 01:00:00 +0200},
      biburl = {https://dblp.org/rec/journals/corr/abs-2104-11560.bib},
      bibsource = {dblp computer science bibliography, https://dblp.org},
    }

2019