Semantic Change Characterization with LLMs using Rhetorics

TL;DR

This paper explores how large language models can be used to characterize different types of semantic change in language by combining Chain-of-Thought reasoning with rhetorical devices, supported by experimental evaluation.

Contribution

It introduces a novel approach that leverages LLMs with rhetorical devices to analyze semantic change, validated through new datasets and experimental assessment.

Findings

LLMs effectively capture semantic change types

Rhetorical devices enhance LLM reasoning capabilities

Experimental results demonstrate improved semantic analysis

Abstract

Languages continually evolve in response to societal events, resulting in new terms and shifts in meanings. These changes have significant implications for computer applications, including automatic translation and chatbots, making it essential to characterize them accurately. The recent development of LLMs has notably advanced natural language understanding, particularly in sense inference and reasoning. In this paper, we investigate the potential of LLMs in characterizing three types of semantic change: dimension, relation, and orientation. We achieve this by combining LLMs' Chain-of-Thought with rhetorical devices and conducting an experimental assessment of our approach using newly created datasets. Our results highlight the effectiveness of LLMs in capturing and analyzing semantic changes, providing valuable insights to improve computational linguistic applications.