Measuring Distributional Similarity in Context

The computation of meaning similarity as operationalized by vector-based models has found widespread use in many tasks ranging from the acquisition of synonyms and paraphrases to word sense disambiguation and textual entailment. Vector-based models are typically directed at representing words in isolation and thus best suited for measuring similarity out of context. In his paper we propose a probabilistic framework for measuring similarity in context. Central to our approach is the intuition that word meaning is represented as a probability distribution over a set of latent senses and is modulated by context. Experimental results on lexical substitution and word similarity show that our algorithm outperforms previously proposed models.

• Type: Journal
• Year: 2010
• Where: EMNLP
• Authors: Georgiana Dinu, Mirella Lapata
• Keywords: EMNLP 2010, Natural Language Processing, Textual Entailment, Vector-based Models, Word Similarity