معرفی
Thien Nguyen is an Associate Professor in the Department of Computer Science at the University of Oregon, within the College of Arts and Sciences. His research focuses on natural language processing, information extraction, and deep learning, with an emphasis on multilingual and large-scale language models.
- Ph.D., Computer Science, New York University
- M.S., Computer Science, New York University
- B.S., Computer Science, Hanoi University of Science and Technology
His research explores how computers can understand human language to perform cognitive tasks, particularly by distilling structured information from massive multilingual text. He is a pioneer in applying deep learning to information extraction and has developed influential models and datasets such as CulturaX, Vistral, and Okapi. His lab designs learning algorithms for NLP tasks including event detection, machine translation, and chatbots. The recent work centers on large language models, cross-lingual transfer, and continual learning.
His 15 most recent publications reflect a strong trend in multilingual NLP, large language models, event and relation extraction, and active and continual learning. These works span dataset creation, model development, and evaluation frameworks, often leveraging transformer architectures and reinforcement learning. The research is highly interdisciplinary, combining data mining, machine learning, and linguistic analysis.
- NSF CAREER Award (2023)
- Best Demo Paper Award, EACL 2021
- Outstanding Demo Paper Award, EACL 2021
- IBM Ph.D. Fellowship (2016)
- Dean's Dissertation Fellowship, NYU
- Harold Grad Prize, NYU
Dr. Nguyen advises multiple Ph.D. and M.S. students and has secured significant research funding from the NSF, IARPA, and Adobe Research. His lab, UO-NLP, is actively developing tools like Trankit and FourIE. He teaches courses in data structures, machine learning, and NLP, and serves on the program and senior committees of top-tier conferences such as ACL, EMNLP, and NeurIPS. He is deeply involved in advancing multilingual NLP and democratizing access to language technologies across diverse languages.
