Causal interventions expose implicit situation models for commonsense language understanding

Takateru Yamakoshi, James L. McClelland, Adele E. Goldberg, Robert D. Hawkins

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Accounts of human language processing have long appealed to implicit “situation models” that enrich comprehension with relevant but unstated world knowledge. Here, we apply causal intervention techniques to recent transformer models to analyze performance on the Winograd Schema Challenge (WSC), where a single context cue shifts interpretation of an ambiguous pronoun. We identify a relatively small circuit of attention heads that are responsible for propagating information from the context word that guides which of the candidate noun phrases the pronoun ultimately attends to. We then compare how this circuit behaves in a closely matched “syntactic” control where the situation model is not strictly necessary. These analyses suggest distinct pathways through which implicit situation models are constructed to guide pronoun resolution.

Original languageEnglish (US)
Title of host publicationFindings of the Association for Computational Linguistics, ACL 2023
PublisherAssociation for Computational Linguistics (ACL)
Pages13265-13293
Number of pages29
ISBN (Electronic)9781959429623
StatePublished - 2023
Event61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada
Duration: Jul 9 2023Jul 14 2023

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
Country/TerritoryCanada
CityToronto
Period7/9/237/14/23

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Causal interventions expose implicit situation models for commonsense language understanding'. Together they form a unique fingerprint.

Cite this