A Wind of Change: Detecting and Evaluating Lexical Semantic Change across Times and Domains

TL;DR

This paper introduces a comprehensive evaluation framework for detecting lexical semantic changes over time and across domains, addressing previous limitations and demonstrating the applicability of models in both diachronic and synchronic contexts.

Contribution

It provides a unified benchmarking approach for semantic change detection and extends its application to domain-specific sense divergence detection in term extraction.

Findings

Benchmark models show consistent performance across tasks

Evaluation framework improves comparability of semantic change detection methods

Models effectively detect semantic divergences across time and domains

Abstract

We perform an interdisciplinary large-scale evaluation for detecting lexical semantic divergences in a diachronic and in a synchronic task: semantic sense changes across time, and semantic sense changes across domains. Our work addresses the superficialness and lack of comparison in assessing models of diachronic lexical change, by bringing together and extending benchmark models on a common state-of-the-art evaluation task. In addition, we demonstrate that the same evaluation task and modelling approaches can successfully be utilised for the synchronic detection of domain-specific sense divergences in the field of term extraction.