Topic Models for Meaning Similarity in Context

Recent work on distributional methods for similarity focuses on using the context in which a target word occurs to derive context-sensitive similarity computations. In this paper we present a method for computing similarity which builds vector representations for words in context by modeling senses as latent variables in a large corpus. We apply this to the Lexical Substitution Task and we show that our model significantly outperforms typical distributional methods.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Georgiana Dinu, Mirella Lapata
• Keywords: COLING 2010, Computational Linguistics, Context-sensitive Similarity Computations, Distributional Methods, Typical Distributional Methods