SEMANTIC SIMILARITY KNOWLEDGE AND ITS APPLICATIONS
Diana Zaiu Inkpen · 2007
Abstract. Semantic relatedness refers to the degree to which two concepts or words are related. Humans are able to easily judge if a pair of words are related in some way. For example, most people would agree that apple and orange are more related than are apple and toothbrush. Semantic similarity is a subset of semantic relatedness. In this article we describe several methods for computing the similarity of two words, following two directions: dictionary-based methods that use WordNet, Roget’s thesaurus, or other resources; and corpus-based methods that use frequencies of co-occurrence in corpora (cosine method, latent semantic indexing, mutual information, etc). Then, we present results for several applications of word similarity knowledge: solving TOEFL-style synonym questions, detecting words that do not fit into their context in order to detect speech recognition errors, and synonym choice in context, for writing aid tools. We also present a method for computing the similarity of two short texts, based on the similarities of their words. Applications of text similarity knowledge include: designing exercises