Semantic Change Characterization with LLMs using Rhetorics
This work addresses the need for accurate semantic change characterization to improve computational linguistic applications like translation and chatbots, though it appears incremental by applying existing LLM techniques to a specific domain.
The paper tackled the problem of characterizing semantic changes in language using LLMs, achieving effective capture and analysis of three types of semantic change (dimension, relation, orientation) through a combination of Chain-of-Thought reasoning and rhetorical devices, as demonstrated on newly created datasets.
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.