Semantic Change Characterization with LLMs using Rhetorics
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 LLM in capturing and analyzing semantic changes, providing valuable insights to improve computational linguistic applications.
Paper Type: Long
Research Area: Semantics: Lexical and Sentence-Level
Research Area Keywords: lexical semantic change, rhetorics, large language models
Contribution Types: Model analysis & interpretability, Approaches to low-resource settings, Data resources
Languages Studied: english
Submission Number: 954
Loading