| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Wed, 12 Nov 2025 00:24:14 GMT
access-control-allow-origin: *
etag: W/"6913d3ae-be15"
expires: Mon, 29 Dec 2025 13:43:25 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 9EAB:3FD64F:8E3047:9F9057:69528319
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 16:12:11 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210031-BOM
x-cache: HIT
x-cache-hits: 0
x-timer: S1767024731.964720,VS0,VE207
vary: Accept-Encoding
x-fastly-request-id: de5d7df5df0aa5dc0476065abcd8ed85c757d9e7
content-length: 13137
Eunsol Choi
Assistant Professor
Eunsol Choi
Assistant Professor
Computer Science
Data Science
CILVR at NYU
ML2
Data Science
CILVR at NYU
ML2
Office 600, 60 5th Avenue, New York, NY 10011
Email: firstname@nyu.edu
I am an assistant professor in Computer Science (Courant Institute) and Data Science at New York University. I was an assistant professor in the Computer Science department at the University of Texas at Austin from 2020. Before UT, I was a researcher at Google AI in NYC and a Ph.D. student at UW, advised by Luke Zettlemoyer and Yejin Choi.
I enjoy studying real world language usages with simple and generalizable models. I also build benchmarks that allows us to evaluate NLP models, conduct model analysis, and bring the progresses in English NLP to a wider range of languages. Here are research topics that I am currently interested in:
- Continual Learning and Knowledge Editing: While LMs retain vast amounts of world knowledge seen during pretraining, such knowledge can get outdated. I am interested in retrieval augmentation and updating parametric knowledge in LMs.
- Long-form Question Answering: Enabling systems to produce paragraph-level answers opens up possibilities to handle more complicated questions and provide more comprehensive answers. LFQA merges two challenging research areas -- information retrieval and text generation. Furthermore, we have to synthesize information from multiple documents.
- Human-LM Interaction: NLP systems are getting deployed fast and widely. I am interested in improving human interactions with LM, for example, how should we present information such that users will not be misled by plausible yet imperfect model predictions? The deployment of models also creates opportunities to learn from interaction with users.
- Spoken Language Processing: Spoken language exhibits richer prosodic features that are absent in written text. Can we build textless NLP system which can work on speech signals, opening doors to handle languages without written scripts?