ClaC: Semantic Relatedness of Words and Phrases

Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Seventh International Workshop on Semantic Evaluation (SemEval 2013), pages 108–113, Atlanta, Georgia, June 14-15, 2013. c⃝2013 Association for Computational Linguistics ClaC: Semantic Relatedness of Words and Phrases Reda Siblini Concordia University 1400 de Maisonneuve Blvd. West Montreal, Quebec, Canada, H3G 1M8 r_sibl@encs.concordia.ca Leila Kosseim Concordia University 1400 de Maisonneuve Blvd. West Montreal, Quebec, Canada, H3G 1M8 kosseim@encs.concordia.ca Abstract The measurement of phrasal semantic relat- edness is an important metric for many nat- ural language processing applications. In this paper, we present three approaches for mea- suring phrasal semantics, one based on a se- mantic network model, another on a distribu- tional similarity model, and a hybrid between the two. Our hybrid approach achieved an F- measure of 77.4% on the task of evaluating the semantic similarity of words and compo- sitional phrases. 1 Introduction Phrasal semantic relatedness is a measurement of how multiword expressions are related in meaning. Many natural language processing applications such as textual entailment, question answering, or information retrieval require a robust measurement of phrasal semantic relatedness. Current approaches to address this problem can be categorized into three main categories: those that rely on a knowledge base and its structure, those that use the distribu- tional hypothesis on a large corpus, and hybrid approaches. In this paper, we propose supervised approaches for comparing phrasal semantics that are based on a semantic network model, a distributional similarity model, and a hybrid between the two. Those approaches have been evaluated on the task of semantic similarity of words and compositional phrases and on the task of evaluating the composi- tionality of phrases in context. 2 Semantic Similarity of Words and Compositional Phrases The semantic similarity of words and compositional phrases is the task of evaluating the similarity of a word and a short phrase of two or more words; for example, the word Interview and the phrase Formal Meeting. In the next section we present our seman- tic network model for computing phrasal semantic relatedness between a word and a phrase, followed by a distributional similarity model, that we evalu- ate on the task of semantic similarity of words and compositional phrases. 2.1 Semantic Network Model Knowledge-based approaches to semantic related- ness use the features of the knowledge base to mea- sure the relatedness. One of most frequently used semantic network is the Princeton’s WordNet (Fell- baum, 1998) which groups words into synonyms sets (called synsets) and includes 26 semantic rela- tions between those synsets, including: hypernymy, hyponymy, meronymy, entailment ... To measure relatedness, most of those approaches rely on the structure of the semantic network, such as the semantic link path, depth (Leacock and Chodorow, 1998; Wu and Palmer, 1994), direction (Hirst and St-Onge, 1998), or type (Tsatsaronis et al., 2010). Our phrasal semantic relatedness ap- proach is inspired from those methods. However, our approach is based on the idea that the combi- nation of the least costly types of relations that re- late one concept to …

Content truncated to 500 words