Latent Compositional Representations for English Function Word Comprehension

This paper investigates whether biasing natural language models toward tree-compositional structure and systematic token representation can improve performance on tasks that require the use of function words. The method used treats tree-structure as latent and thus requires no gold parse labels. Results show that across four function-word-focused NLI probing tasks, tree-compositional models perform as well as LSTMs, but lag behind BERT to varying degrees between tasks. Context-dependent behavior of tree-compositional models highlights a potential weakness of the architecture in the absence of grounding information.

Author dc:creator

• Barnes, Megan

Advisor dc:contributor.advisor

• Steinert-Threlkeld, Shane

• Linguistics
• Computer science

Statement dc:rights

• CC BY

Language dc:language.iso

en_US

Handle dc:identifier.uri

http://hdl.handle.net/1773/48282

OAI identifier oai:identifier

oai:digital.lib.washington.edu:1773/48282