Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models

Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We assess the ability of modern neural language models to reproduce this behavior in English and evaluate the effect of stru...

Full description

Bibliographic Details
Main Authors: Wilcox, Ethan, Qian, Peng, Futrell, Richard, Kohita, Ryosuke, Levy, Roger, Ballesteros, Miguel
Other Authors: Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Format: Article
Language:English
Published: Association for Computational Linguistics (ACL) 2021
Online Access:https://hdl.handle.net/1721.1/138280

Internet

https://hdl.handle.net/1721.1/138280

Similar Items