Paper: Topic Models for Meaning Similarity in Context

ACL ID C10-2029
Title Topic Models for Meaning Similarity in Context
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

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 com- puting similarity which builds vector rep- resentations for words in context by mod- eling senses as latent variables in a large corpus. We apply this to the Lexical Sub- stitution Task and we show that our model significantly outperforms typical distribu- tional methods.