Compositional Generalization in a Graph-based Model of Distributional Semantics

Shufan Mao, Philip A. Huebner, Jon A. Willits

Research output: Contribution to conferencePaperpeer-review

Abstract

A critical part of language comprehension is inferring omitted but plausible information from linguistic descriptions of events. For instance, the verb phrase 'preserve vegetable' implies the instrument vinegar whereas 'preserve fruit' implies dehydrator. We studied the ability of distributional semantic models to perform this kind of semantic inference after being trained on an artificial corpus with strictly controlled constraints on which verb phrases occur with which instruments. Importantly, the ability to infer omitted but plausible instruments in our task requires compositional generalization. We found that contemporary neural network models fall short generalizing learned selectional constraints, and that a graph-based distributional semantic model trained on constituency-parsed data and equipped with a spreading-activation procedure for calculating semantic relatedness, achieves perfect performance. Our findings shed light on the mechanisms that give rise to compositional generalization, and using graphs to model semantic memory.

Original languageEnglish (US)
Pages1993-1999
Number of pages7
StatePublished - 2022
Externally publishedYes
Event44th Annual Meeting of the Cognitive Science Society: Cognitive Diversity, CogSci 2022 - Toronto, Canada
Duration: Jul 27 2022Jul 30 2022

Conference

Conference44th Annual Meeting of the Cognitive Science Society: Cognitive Diversity, CogSci 2022
Country/TerritoryCanada
CityToronto
Period7/27/227/30/22

Keywords

  • distributional semantics
  • semantic inference

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Human-Computer Interaction
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Compositional Generalization in a Graph-based Model of Distributional Semantics'. Together they form a unique fingerprint.

Cite this