Research
My research asks how the people who build and use language technologies can shape their development. I study how practitioners make decisions when data and tools are scarce, and when we need to involve people directly to tell whether a system is useful in practice.
In an ongoing cross-lingual question answering project, I ask whether automatic translation metrics and model performance tell us how well people can answer comprehension questions using machine-translated passages.
In earlier work, I interviewed practitioners about the challenges they face building tools for low-resource Sino-Tibetan languages and surveyed NLP research on those languages. I also studied how well named entity recognition models generalize over time.
Publications
- EMNLP 2026 Behind-the-Scenes Challenges in Sino-Tibetan Low-Resource Language Technology Development
- EMNLP 2025 Africa Health Check: Probing Cultural Bias in Medical LLMs
- COMPASS 2025 Community-Driven Data Practices for Advancing Ethical and Equitable AI in Low-Resource Language Contexts
- NAACL 2025 A Survey of NLP Progress in Sino-Tibetan Low-Resource Languages
- NAACL 2024 Universal NER: A Gold-Standard Multilingual Named Entity Recognition Benchmark
- ACL 2023 · Reproduction Award Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?
About
I am a PhD student in the School of Interactive Computing at Georgia Tech, advised by Michael L. Best in the T+ID Lab. I earned a B.S. in Computer Science and a B.A. in Linguistics at the University of Washington, where I worked with Luke Zettlemoyer and Terra Blevins.