On the Distinctive Co-occurrence Characteristics of Antonymy

2025/09/15 by Zhihan Cao, Cao, Zhihan, Hiroaki Yamada +3 · 1 citation
Computer Science · #Advanced Algebra and Logic #Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2509.11534

openalex publication_date 2025/09/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Antonymy has long received particular attention in lexical semantics. Previous studies have shown that antonym pairs frequently co-occur in text, across genres and parts of speech, more often than would be expected by chance. However, whether this co-occurrence pattern is distinctive of antonymy remains unclear, due to a lack of comparison with other semantic relations. This work fills the gap by comparing antonymy with three other relations across parts of speech using robust co-occurrence metrics. We find that antonymy is distinctive in three respects: antonym pairs co-occur with high strength, in a preferred linear order, and within short spans. All results are available online.

Citations

• Misalignment of Semantic Relation Knowledge between WordNet and Human Intuition
• Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora
• HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment
• The Nonparametric Behrens-Fisher Problem: Asymptotic Theory and a Small-Sample Approximation

Cited by

• Relation Geometry in Semantic Space of Language Models

Related

• Shallowly accurate but deeply confused – how language models deal with antonyms
• Antonym vs Synonym Distinction using InterlaCed Encoder NETworks (ICE-NET)
• Integrating Distributional Lexical Contrast into Word Embeddings for\n Antonym-Synonym Distinction
• A Comprehensive Evaluation of Semantic Relation Knowledge of Pretrained Language Models and Humans
• Computing Lexical Contrast