Skip to main navigation Skip to search Skip to main content

When Polysemy Matters: Modeling Semantic Categorization with Word Embeddings

  • SUNY Buffalo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Recent work using word embeddings to model semantic categorization have indicated that static models outperform the more recent contextual class of models (Majewska et al., 2021). In this paper, we consider polysemy as a possible confounding factor, comparing sense-level embeddings with previously studied static embeddings on both coarse- and fine-grained categorization tasks. We find that the effect of polysemy depends on how one defines semantic categorization; while sense-level embeddings dramatically outperform static embeddings in predicting coarse-grained categories derived from a word sorting task, they perform approximately equally in predicting fine-grained categories derived from context-free similarity judgments. Our findings highlight the different processes underlying human behavior on different types of semantic tasks.

Original languageEnglish
Title of host publication*SEM 2022 - 11th Joint Conference on Lexical and Computational Semantics, Proceedings of the Conference
EditorsVivi Nastase, Ellie Pavlick, Mohammad Taher Pilehvar, Jose Camacho-Collados, Alessandro Raganato
PublisherAssociation for Computational Linguistics (ACL)
Pages123-131
Number of pages9
ISBN (Electronic)9781955917988
StatePublished - 2022
Event11th Joint Conference on Lexical and Computational Semantics, StarSEM 2022 - Hybrid, Seattle, United States
Duration: Jul 14 2022Jul 15 2022

Publication series

Name*SEM 2022 - 11th Joint Conference on Lexical and Computational Semantics, Proceedings of the Conference

Conference

Conference11th Joint Conference on Lexical and Computational Semantics, StarSEM 2022
Country/TerritoryUnited States
CityHybrid, Seattle
Period07/14/2207/15/22

Fingerprint

Dive into the research topics of 'When Polysemy Matters: Modeling Semantic Categorization with Word Embeddings'. Together they form a unique fingerprint.

Cite this