This site is currently broken for new queries. It seems like some bot hit it and we ran out of exa credits.
Enter your personal website to find others like you. Powered by Exa's "find similar". Built on Val Town.
Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical World.
This is usually done through two separate models, a retriever that encodes the query and finds nearest neighbors, and a reader based on Transformers.
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
I have broad interests in language technologies, especially information retrieval, information extraction, and machine learning approaches in these a…
Best Paper Award, Collaboration, Electronic Messaging, Anti-abuse, and Spam, 2011
title = {Knowledge Exploration using Tables on the Web},
See the tabs above for more information about my research and teaching.
The theme of my research has been developing effective machine learning systems for natural language understanding.
Automatic Compositor Attribution in the First Folio of Shakespeare