Derry Wijaya

Monash University Indonesia | Boston University (Adjunct) | Jakarta, Indonesia | Derry.Wijaya@monash.edu

prof_pic.jpg

I am an Associate Professor and the Program Coordinator for the Data Science Program at Monash University Indonesia. I also serve as the co-director of the Monash Data and Democracy Research Hub, an interdisciplinary lab focused on analyzing and researching the impact of data and technology on democracy in the digital age.

My current research interests lie primarily in the areas of multilingual and low-resource Natural Language Processing and in improving the performance and alignment of Language Models through self-consistency, critiques, reasoning, and in-context learning. I am also deeply engaged in analyzing framing, bias, toxicity, and misinformation within AI models and public communications.

Before moving back home and joining Monash, I was an Assistant Professor in the Computer Science Department at Boston University. I am a Fulbrighter, I earned my Ph.D. at Carnegie Mellon University’s Language Technologies Institute, where I was advised by Tom Mitchell. Following that, I completed a postdoctoral fellowship at the University of Pennsylvania under the guidance of Chris Callison-Burch. I hold both a Bachelor’s and a Master’s degree in Computing from the National University of Singapore, where I worked with Stephane Bressan as my advisor.

I serve as a program committee, area chair, senior area chair, session and local organizer chair for various machine learning and natural language processing conferences such as ACL, EMNLP, IJCNLP, NeurIPS, ICLR, and journals.

news

Dec 16, 2024 I just learned about the sudden passing of my undergraduate and master’s advisor. Stéphane was the professor who first introduced me to research. He took a chance on me and involved me—an undergraduate at the time—in his research projects. Since then, I have followed his example by involving undergraduate students in my own research. I will always be grateful for his constant support, friendship, and kindness; and will miss him deeply.
Dec 14, 2024 In the process of updating my website after so long! :sparkles:

selected publications

2024

  1. ACL-findings
    Deductive closure training of language models for coherence, accuracy, and updatability
    Afra Feyza Akyürek, Ekin Akyürek, Leshem Choshen, and 2 more authors
    arXiv preprint arXiv:2401.08574, 2024
    DOI URL
  2. LREC
    Mitigating Translationese in Low-resource Languages: The Storyboard Approach
    Garry Kuwanto, Eno-Abasi E Urua, Priscilla Amondi Amuok, and 8 more authors
    arXiv preprint arXiv:2407.10152, 2024
    DOI URL
  3. INLG
    Generating Faithful and Salient Text from Multimodal Data
    Tahsina Hashem, Weiqing Wang, Derry Tanti Wijaya, and 2 more authors
    arXiv preprint arXiv:2409.03961, 2024
    DOI URL
  4. pre-print
    Metametrics: Calibrating metrics for generation tasks using human preferences
    Genta Indra Winata, David Anugraha, Lucky Susanto, and 2 more authors
    arXiv preprint arXiv:2410.02381, 2024
    DOI URL
  5. pre-print
    WORLDCUISINES: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
    Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan, and 8 more authors
    arXiv preprint arXiv:2410.12705, 2024
    DOI URL
  6. WMT
    METAMETRICS-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration
    David Anugraha, Garry Kuwanto, Lucky Susanto, and 2 more authors
    arXiv preprint arXiv:2411.00390, 2024
    DOI URL
  7. EMNLP-demo
    Monitoring Hate Speech in Indonesia: An NLP-based Classification of Social Media Texts
    Musa Wijanarko, Lucky Susanto, Prasetia Pratama, and 3 more authors
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2024
    DOI URL

2023

  1. ACL
    Rl4f: Generating natural language feedback with reinforcement learning for repairing model outputs
    Afra Feyza Akyürek, Ekin Akyürek, Aman Madaan, and 4 more authors
    arXiv preprint arXiv:2305.08844, 2023
    DOI URL
  2. opinion
    Pentingnya Dekolonisasi AI di Era Model Bahasa Besar
    Derry Wijaya
    2023
    URL
  3. opinion
    Mengapa menghentikan penelitian dan eksperimen terkait teknologi ChatGPT bukan solusi jitu
    Arif Perdana, and Derry Wijaya
    2023
    URL
  4. opinion
    POV: With ChatGPT’s Arrival, Should Educators Be Mourning the End of the College Essay?
    Naomi Caselli, Christina Dobbs, and Derry Wijaya
    2023
    URL
  5. NewMedia&Soc
    Effects of# coronavirus content moderation on misinformation and anti-Asian hate on Instagram
    Traci Hong, Zilu Tang, Manyuan Lu, and 3 more authors
    new media & society, 2023
    DOI URL
  6. INLG
    Generating faithful text from a knowledge graph with noisy reference text
    Tahsina Hashem, Weiqing Wang, Derry Tanti Wijaya, and 2 more authors
    arXiv preprint arXiv:2308.06488, 2023
    DOI URL
  7. ACII
    The Affective Nature of AI-Generated News Images: Impact on Visual Journalism
    Sejin Paik, Sarah Bonna, Ekaterina Novozhilova, and 4 more authors
    In 2023 11th International Conference on Affective Computing and Intelligent Interaction (ACII), 2023
    DOI URL
  8. EMNLP-findings
    Explain-then-translate: an analysis on improving program translation with self-generated explanations
    Zilu Tang, Mayank Agarwal, Alex Shypula, and 4 more authors
    arXiv preprint arXiv:2311.07070, 2023
    DOI URL
  9. EMNLP
    Dune: Dataset for unified editing
    Afra Feyza Akyürek, Eric Pan, Garry Kuwanto, and 1 more author
    arXiv preprint arXiv:2311.16087, 2023
    DOI URL
  10. EMNLP
    COVID-19 vaccine misinformation in middle income countries
    Jongin Kim, Byeo Rhee Bak, Aditya Agrawal, and 4 more authors
    In Empirical Methods in Natural Language Processing 2023, 2023
    DOI URL

2022

  1. ICLR
    Subspace Regularizers for Few-Shot Class Incremental Learning
    Afra Feyza Akyürek, Ekin Akyürek, Derry Wijaya, and 1 more author
    In ICLR, 2022
    DOI URL
  2. NAACL-findings
    On Measuring Social Biases in Prompt-Based Multi-Task Learning
    Afra Feyza Akyürek, Sejin Paik, Muhammed Yusuf Kocyigit, and 3 more authors
    In Findings of NAACL 2022, 2022
    DOI URL
  3. NAACL-workshop
    Challenges in Measuring Bias via Open-Ended Language Generation
    Afra Feyza Akyürek, Muhammed Yusuf Kocyigit, Sejin Paik, and 1 more author
    In Gender Bias in NLP Workshop at NAACL 2022, 2022
    DOI URL
  4. AACL
    AugCSE: Contrastive Sentence Embedding with Diverse Augmentations
    Zilu Tang, Muhammed Yusuf Kocyigit, and Derry Wijaya
    arXiv preprint arXiv:2210.13749, 2022
    DOI URL

2021

  1. NAACL
    Cultural and geographical influences on image translatability of words across languages
    Nikzad Khani, Isidora Chara Tourni, Mohammad Sadegh Rasooli, and 2 more authors
    In North American Association for Computational Linguistics 2021, 2021
    DOI URL
  2. EMNLP-demo
    OpenFraming: open-sourced tool for computational framing analysis of multilingual data
    Vibhu Bhatia, Vidya Prasad Akavoor, Sejin Paik, and 8 more authors
    In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2021
    DOI URL

2020

  1. ACL
    Multi-label and multilingual news framing analysis
    Afra Feyza Akyürek, Lei Guo, Randa Elanwar, and 3 more authors
    In Proceedings of the 58th annual meeting of the association for computational linguistics, 2020
    DOI URL

2019

  1. CoNLL
    Detecting frames in news headlines and its application to analyzing news framing trends surrounding US gun violence
    Siyi Liu, Lei Guo, Kate Mays, and 2 more authors
    In Proceedings of the 23rd conference on computational natural language learning (CoNLL), 2019
    DOI URL

2018

  1. ACL
    Learning translations via images with a massively multilingual image dataset
    John Hewitt, Daphne Ippolito, Brendan Callahan, and 3 more authors
    In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018
    DOI URL
  2. ACM
    Never-ending learning
    Tom Mitchell, William Cohen, Estevam Hruschka, and 8 more authors
    Communications of the ACM, 2018
    DOI URL

2011

  1. DETECT
    Understanding semantic change of words over centuries
    Derry Tanti Wijaya, and Reyyan Yeniterzi
    In Proceedings of the 2011 international workshop on DETecting and Exploiting Cultural diversiTy on the social web, 2011
    DOI URL

2010

  1. NYTimes
    Aiming to learn as we do, a machine teaches itself
    STEVE Lohr
    The New York Times, http://www. nytimes. com/2010/10/05/science/05compute. html, 2010
    URL