Article

Extracting Semantic Representations from Word Co-occurrence Statistics: Polysemes and Homonyms

2026-05-14

Abstract excerpt

<p>Vectors of word co-occurrence statistics from large corpora of natural language have previously been shown to provide good representations of lexical semantics and are now widely used resources in numerous language applications and models of human behaviour. This paper explores the open question of how the blending of multiple word meanings associated with polysemy and homonymy affect the quality of those corpu...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: f0bf6351-65fc-5545-875d-7fcddb4daa6e
DOI: 10.31234/osf.io/yf3v7_v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Extracting Semantic Representations from Word Co-occurrence Statistics: Polysemes and HomonymsDOI 10.31234/osf.io/yf3v7_v1Read

Designing Vocabulary Multiple-Choice Tests For Exploring Word Frequency Effects In Distributional SemanticsSemantic proximity Read

Conceptual Relations Predict Colexification across LanguagesSemantic proximity Read

Meaning Beyond Lexicality: Capturing Pseudoword Definitions with Language ModelsSemantic proximity Read

What is Semantic Distance? A Review and Proposed Method for Modeling Conceptual Transitions in Natural LanguageSemantic proximity Read

A large-scale analysis of metonymy across languagesSemantic proximity Read

Success and Failure of Compositional Generalization in Distributional Models of LanguageSemantic proximity Read

Latent diversity in human conceptsSemantic proximity Read

Metonymy as a Universal Cognitive Phenomenon: Evidence from Multilingual LexiconsSemantic proximity Read

Leveraging Context for Perceptual Prediction using Word EmbeddingsSemantic proximity Read