Misalignment of Semantic Relation Knowledge between WordNet and Human Intuition

TL;DR

This paper systematically compares WordNet's semantic relations with human intuition, revealing significant misalignments especially in synonymy and taxonomic relations, and questions the reliability of WordNet path length as an indicator of these relations.

Contribution

It provides the first comprehensive analysis of the alignment between WordNet's semantic relations and human intuition, highlighting areas for improvement.

Findings

Significant misalignment between WordNet and human intuition in semantic relations.

Systematic pattern of mismatch in synonymy and taxonomic relations.

WordNet path length is unreliable for indicating hypernymy or hyponymy.

Abstract

WordNet provides a carefully constructed repository of semantic relations, created by specialists. But there is another source of information on semantic relations, the intuition of language users. We present the first systematic study of the degree to which these two sources are aligned. Investigating the cases of misalignment could make proper use of WordNet and facilitate its improvement. Our analysis which uses templates to elicit responses from human participants, reveals a general misalignment of semantic relation knowledge between WordNet and human intuition. Further analyses find a systematic pattern of mismatch among synonymy and taxonomic relations~(hypernymy and hyponymy), together with the fact that WordNet path length does not serve as a reliable indicator of human intuition regarding hypernymy or hyponymy relations.