About
I’m an Associate Solutions Architect at Amazon Web Services and a researcher working on machine translation for endangered languages. My research focuses on the Formosan languages of Taiwan with Dr. Emily Prud’hommeaux and the AI4 Communication Sciences Lab.
I graduated cum laude from Boston College in 2026 with a B.A. in Computer Science and a B.S. in Management. Previously: Pushkin Project, Data Structures teaching, and president of the Computer Science Society.
Selected publications
FormosanMT: A Multilingual Parallel Corpus of the Formosan Language Family
Integrating diverse corpora for training an endangered language machine translation system
Paper PDF ACL Anthology Recorded talk Translation demo (restricted)
Software
- Kakarayan. The public search, learning, and research interface for FormosanBank.
- TAME-MT. Machine translation evaluation that accounts for the data a system was trained on.
News
- A Family Affair accepted to EMNLP 2026, Main Conference.
- Graduated cum laude from Boston College.
- Presented FormosanMT at LREC 2026.
- FormosanMT accepted to LREC 2026.
- Published an NLLB-200 fine-tuning tutorial.
- Contributed to Hugging Face Transformers.
- Featured in the Wall Street Journal Future View.
- Presented Amis machine translation work at ComputEL-8.