Litcius/Paper detail

LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical Substitution

George Michalopoulos, Ian McKillop, Alexander Wong, Helen Chen

2022Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)15 citationsDOIOpen Access PDF

Abstract

Lexical substitution is the task of generating meaningful substitutes for a word in a given textual context. Contextual word embedding models have achieved state-of-the-art results in the lexical substitution task by relying on contextual information extracted from the replaced word within the sentence. However, such models do not take into account structured knowledge that exists in external lexical databases.

Topics & Concepts

Substitution (logic)Computer scienceNatural language processingArtificial intelligenceEmbeddingContext (archaeology)SentenceWord (group theory)Task (project management)Similarity (geometry)Benchmark (surveying)Lexical itemLinguisticsProgramming languageBiologyGeodesyPaleontologyGeographyPhilosophyImage (mathematics)EconomicsManagementNatural Language Processing TechniquesTopic ModelingText Readability and Simplification
LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical Substitution | Litcius