Work

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

Year: 2023

Type: conference-paper

Abstract: 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.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2023.acl-long.176

Authors: Mario Giulianelli, Iris Luden, Raquel Fernandez, Andrey Kutuzov

Institutions: University of Oslo, University of Amsterdam

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: European Commission

Awards: G2388848714, G434337789