no code implementations • 20 Mar 2024 • Catherine Arnett, Pamela D. Rivière, Tyler A. Chang, Sean Trott
The relationship between language model tokenization and performance is an open area of research.
1 code implementation • 4 Sep 2022 • Sean Trott, Cameron Jones, Tyler Chang, James Michaelov, Benjamin Bergen
Humans can attribute beliefs to others.
1 code implementation • 10 Mar 2022 • Sean Trott, Benjamin Bergen
Most large language models are trained on linguistic input alone, yet humans appear to ground their understanding of words in sensorimotor experience.
no code implementations • ACL 2021 • Sean Trott, Benjamin Bergen
Most words are ambiguous{---}-i. e., they convey distinct meanings in different contexts{---}-and even the meanings of unambiguous words are context-dependent.
1 code implementation • 27 May 2021 • Sean Trott, Benjamin Bergen
Most words are ambiguous--i. e., they convey distinct meanings in different contexts--and even the meanings of unambiguous words are context-dependent.
no code implementations • ACL 2020 • Sean Trott, Tiago Timponi Torrent, Nancy Chang, Nathan Schneider
Human speakers have an extensive toolkit of ways to express themselves.
1 code implementation • 23 Jul 2016 • Steve Doubleday, Sean Trott, Jerome Feldman
This is a challenge to handle in a natural language understanding system.
no code implementations • 22 Apr 2016 • Manfred Eppe, Sean Trott, Jerome Feldman
We develop a natural language interface for human robot interaction that implements reasoning about deep semantics in natural language.