Definition generation for lexical semantic change detection
This work addresses the problem of tracking how word meanings evolve over time for linguists and NLP researchers, offering an incremental improvement with enhanced interpretability.
The authors tackled lexical semantic change detection by using contextualized word definitions generated by large language models as semantic representations, showing that this approach performs on par with or outperforms prior non-supervised methods across five datasets and three languages.
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.