Definition generation for lexical semantic change detection

TL;DR

This paper introduces a method for detecting lexical semantic change over time by using large language models to generate definitions, which serve as sense representations to compare semantic shifts across periods.

Contribution

The paper proposes a novel approach leveraging generated definitions as sense representations for semantic change detection, improving interpretability and performance over previous methods.

Findings

Generated definitions effectively signal semantic change.

The method outperforms prior non-supervised sense-based LSCD approaches.

Approach maintains interpretability and explainability.

Abstract

We use contextualized word definitions generated by large language models as semantic representations in the task of diachronic lexical semantic change detection (LSCD). In short, generated definitions are used as `senses', and the change score of a target word is retrieved by comparing their distributions in two time periods under comparison. On the material of five datasets and three languages, we show that generated definitions are indeed specific and general enough to convey a signal sufficient to rank sets of words by the degree of their semantic change over time. Our approach is on par with or outperforms prior non-supervised sense-based LSCD methods. At the same time, it preserves interpretability and allows to inspect the reasons behind a specific shift in terms of discrete definitions-as-senses. This is another step in the direction of explainable semantic change modeling.