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 Akbar, Jhonson Lee, Nuur Shadieq, Tjeng Wawan Cenggoro, hanung linuwih, Bryan Wilie, Galih Muridan, Genta Winata, David Moeljadi, Alham Fikri Aji, Ayu Purwarianti, and Pascale Fung.

   In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. Nov 2023.

   arXiv Bib PDF Code Poster Slides

   @inproceedings{cahyawijaya-EtAl:2023:ijcnlp,
     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 and Lee, Jhonson and Shadieq, Nuur and Cenggoro, Tjeng Wawan and linuwih, hanung and Wilie, Bryan and Muridan, Galih and Winata, Genta and Moeljadi, David and Aji, Alham Fikri and Purwarianti, Ayu and Fung, Pascale},
     year = {2023},
     month = nov,
     booktitle = {Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
     publisher = {Association for Computational Linguistics},
     address = {Nusa Dua, Bali},
     pages = {921--945},
   }

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

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

   arXiv preprint arXiv:2310.05338. Nov 2023.

   arXiv Bib

   @article{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},
     journal = {arXiv preprint arXiv:2310.05338},
   }

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

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

   In Proceedings of the 2nd Workshop on Natural Language Interfaces (NLint) at the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. Nov 2023.

   arXiv Bib Code Poster

   @inproceedings{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},
     month = nov,
     booktitle = {Proceedings of the 2nd Workshop on Natural Language Interfaces (NLint) at the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
     publisher = {Association for Computational Linguistics},
     address = {Nusa Dua, Bali},
   }

4. 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.

   In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. Nov 2023.

   arXiv Bib PDF Code Poster

   @inproceedings{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},
     month = nov,
     journal = {arXiv preprint arXiv:2302.04023},
     booktitle = {Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
     publisher = {Association for Computational Linguistics},
     address = {Nusa Dua, Bali},
     pages = {675--718},
   }

5. 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. Nov 2023.

   arXiv Bib PDF Supp Code Poster

   @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},
   }

6. 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. Nov 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},
   }

7. 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.

   arXiv Bib PDF Code Poster Slides

   @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},
   }

8. 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. May 2023.

   arXiv Bib Code Slides

   @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}},
   }

9. InstructAlign: Teaching Novel Languages with to LLMs through Alignment-based Crosslingual Instruction

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

   In Proceedings of the 1st Workshop on South East Asian Language Processing (SEALP) at the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. May 2023.

   arXiv Bib Code

   @inproceedings{cahyawijaya2023instruct,
     title = {{InstructAlign: Teaching Novel Languages with to LLMs through Alignment-based Crosslingual Instruction}},
     author = {Cahyawijaya, Samuel and Lovenia, Holy and Yu, Tiezheng and Chung, Willy and Fung, Pascale},
     year = {2023},
     booktitle = {Proceedings of the 1st Workshop on South East Asian Language Processing (SEALP) at the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
     publisher = {Association for Computational Linguistics},
     address = {Nusa Dua, Bali},
   }

10. PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems

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

    In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. Nov 2023.

    arXiv Bib Code Poster

    @inproceedings{wilie-EtAl:2023:ijcnlp,
      title = {{PICK: Polished \& Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems}},
      author = {Wilie, Bryan and Xu, Yan and Chung, Willy and Cahyawijaya, Samuel and Lovenia, Holy and Fung, Pascale},
      year = {2023},
      month = nov,
      booktitle = {Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
      publisher = {Association for Computational Linguistics},
      address = {Nusa Dua, Bali},
      pages = {980--995},
      url = {https://aclanthology.org/2023.ijcnlp-long.63},
    }

2022

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

   Holy Lovenia, Samuel Cahyawijaya, Genta Indra Winata, Peng Xu, Xu Yan, Zihan Liu, Rita Frieske, Tiezheng Yu, Wenliang Dai, Elham J Barezi, and others.

   In Proceedings of the 13th Language Resources and Evaluation Conference (LREC). Nov 2022.

   arXiv Bib Supp Code Poster Slides

   @inproceedings{lovenia2022ascend,
     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 Yan, Xu and Liu, Zihan and Frieske, Rita and Yu, Tiezheng and Dai, Wenliang and Barezi, Elham J and others},
     year = {2022},
     booktitle = {Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},
   }

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

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

   In Proceedings of the 7th Workshop on Representation Learning for NLP (RepL4NLP). Nov 2022.

   arXiv Bib PDF Poster Slides

   @inproceedings{lovenia2022clozer,
     title = {{Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension}},
     author = {Lovenia, Holy and Wilie, Bryan and Chung, Willy and Min, Zeng and Cahyawijaya, Samuel and Su, Dan and Fung, Pascale},
     year = {2022},
     booktitle = {Proceedings of the 7th Workshop on Representation Learning for NLP (RepL4NLP)},
     pages = {60--66},
   }

3. 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.

   arXiv Bib PDF Poster Slides

   @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},
     url = {https://aclanthology.org/2022.latechclfl-1.6},
   }

4. Automatic Speech Recognition Datasets in Cantonese Language: A Survey and a 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, and others.

   In Proceedings of the 13th Language Resources and Evaluation Conference (LREC). Oct 2022.

   arXiv Bib

   @inproceedings{yu2022automatic,
     title = {{Automatic Speech Recognition Datasets in Cantonese Language: A Survey and a 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 others},
     year = {2022},
     booktitle = {Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},
   }

5. CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition

   Wenliang Dai, Samuel Cahyawijaya, Tiezheng Yu, Elham J Barezi, Peng Xu, Cheuk Tung Shadow Yiu, Rita Frieske,  Holy Lovenia, Genta Indra Winata, Qifeng Chen, and others.

   In Proceedings of the 13th Language Resources and Evaluation Conference (LREC). Oct 2022.

   arXiv Bib

   @inproceedings{dai2022ci,
     title = {{CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition}},
     author = {Dai, Wenliang and Cahyawijaya, Samuel and Yu, Tiezheng and Barezi, Elham J and Xu, Peng and Yiu, Cheuk Tung Shadow and Frieske, Rita and Lovenia, Holy and Winata, Genta Indra and Chen, Qifeng and others},
     year = {2022},
     booktitle = {Proceedings of the 13th Language Resources and Evaluation Conference (LREC)},
   }

6. 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. Oct 2022.

   arXiv Bib Poster Slides

   @inproceedings{cahyawijaya2022long,
     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},
     booktitle = {Proceedings of the 13th International Workshop on Health Text Mining and Information Analysis},
     publisher = {EMNLP},
     address = {Abu Dhabi, United Arab Emirates},
   }

7. What Did I Just Hear? Detecting Pornographic Sounds in Adult Videos Using Neural Networks

   Holy Lovenia, Dessi Puji Lestari, and Rita Frieske.

   In Proceedings of the 17th International Audio Mostly Conference. Oct 2022.

   arXiv Bib PDF Poster

   @inproceedings{lovenia2022did,
     title = {{What Did I Just Hear? Detecting Pornographic Sounds in Adult Videos Using Neural Networks}},
     author = {Lovenia, Holy and Lestari, Dessi Puji and Frieske, Rita},
     year = {2022},
     booktitle = {Proceedings of the 17th International Audio Mostly Conference},
     pages = {92--95},
   }

2021

1. Greenformer: Factorization toolkit for efficient deep neural networks

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

   arXiv preprint arXiv:2109.06762. Oct 2021.

   arXiv Bib

   @article{cahyawijaya2021greenformer,
     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 = {arXiv preprint arXiv:2109.06762},
   }

2. Indonesia Expressive Text to Speech System based on Global Style Token and Tacotron 2

   Moch Azhar Dhiaulhaq, Rizki Rivai Ginanjar,  Holy Lovenia, and Dessi Puji Lestari.

   In 2021 8th International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA). Oct 2021.

   Bib PDF

   @inproceedings{dhiaulhaq2021indonesia,
     title = {{Indonesia Expressive Text to Speech System based on Global Style Token and Tacotron 2}},
     author = {Dhiaulhaq, Moch Azhar and Ginanjar, Rizki Rivai and Lovenia, Holy and Lestari, Dessi Puji},
     year = {2021},
     booktitle = {2021 8th International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)},
     pages = {1--6},
     organization = {IEEE},
   }

3. Nora: The well-being coach

   Genta Indra Winata,  Holy Lovenia, Etsuko Ishii, Farhad Bin Siddique, Yongsheng Yang, and Pascale Fung.

   arXiv preprint arXiv:2106.00410. Oct 2021.

   arXiv Bib

   @article{winata2021nora,
     title = {{Nora: The well-being coach}},
     author = {Winata, Genta Indra and Lovenia, Holy and Ishii, Etsuko and Siddique, Farhad Bin and Yang, Yongsheng and Fung, Pascale},
     year = {2021},
     journal = {arXiv preprint arXiv:2106.00410},
   }

2019

1. Speech artifact removal from EEG recordings of spoken word production with tensor decomposition

   Holy Lovenia, Hiroki Tanaka, Sakriani Sakti, Ayu Purwarianti, and Satoshi Nakamura.

   In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Oct 2019.

   arXiv Bib PDF Poster

   @inproceedings{lovenia2019speech,
     title = {{Speech artifact removal from EEG recordings of spoken word production with tensor decomposition}},
     author = {Lovenia, Holy and Tanaka, Hiroki and Sakti, Sakriani and Purwarianti, Ayu and Nakamura, Satoshi},
     year = {2019},
     booktitle = {ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {1115--1119},
     organization = {IEEE},
   }