Papers › Interpretable Word Sense Representations via Definition Generation: The Case of...

Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis

19 May 2023arXiv:2305.11993archive 2025-07-28

Mario Giulianelli, Iris Luden, Raquel Fernandez, Andrey Kutuzov

We propose using automatically generated natural language definitions of contextualised word usages as interpretable word and word sense representations. Given a collection of usage examples for a target word, and the corresponding data-driven usage clusters (i.e., word senses), a definition is generated for each usage with a specialised Flan-T5 language model, and the most prototypical definition in a usage cluster is chosen as the sense label. We demonstrate how the resulting sense labels can make existing approaches to semantic change analysis more interpretable, and how they can allow users -- historical linguists, lexicographers, or social scientists -- to explore and intuitively explain diachronic trajectories of word meaning. Semantic change analysis is only one of many possible applications of the `definitions as representations' paradigm. Beyond being human-readable, contextualised definitions also outperform token or usage sentence embeddings in word-in-context semantic similarity judgements, making them a new promising type of lexical representation for NLP.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ltgoslo/definition_modeling officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingSemantic SimilaritySemantic Textual SimilaritySentenceSentence Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Flan-T5

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections