UNT: SubFinder: Combining Knowledge Sources for Automatic Lexical Substitution

Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), pages 410–413, Prague, June 2007. c⃝2007 Association for Computational Linguistics UNT: SubFinder: Combining Knowledge Sources for Automatic Lexical Substitution Samer Hassan, Andras Csomai, Carmen Banea, Ravi Sinha, Rada Mihalcea∗ Department of Computer Science and Engineering University of North Texas samer@unt.edu, csomaia@unt.edu, carmenb@unt.edu, rss0089@unt.edu, rada@cs.unt.edu Abstract This paper describes the University of North Texas SUBFINDER system. The system is able to provide the most likely set of sub- stitutes for a word in a given context, by combining several techniques and knowl- edge sources. SUBFINDER has successfully participated in the best and out of ten (oot) tracks in the SEMEVAL lexical substitution task, consistently ranking in the first or sec- ond place. 1 Introduction Lexical substitution is defined as the task of identify- ing the most likely alternatives (substitutes) for a tar- get word, given its context (McCarthy, 2002). Many natural language processing applications can bene- fit from the availability of such alternative words, including word sense disambiguation, lexical ac- quisition, machine translation, information retrieval, question answering, text simplification, and others. The task is closely related to the problem of word sense disambiguation, with the substitutes acting as synonyms for the input word meaning. Unlike word sense disambiguation however, lexical substitution is not performed with respect to a given sense inven- tory, but instead candidate synonyms are generated “on the fly” for a given word occurrence. Thus, lexi- cal substitution can be regarded in a way as a hybrid task that combines word sense disambiguation and distributional similarity, targeting the identification of semantically similar words that fit the context. 2 A system for lexical substitution SUBFINDER is a system able to provide the most likely set of substitutes for a word in a given context. ∗Contact author. In SUBFINDER, the lexical substitution task is car- ried out as a sequence of two steps. First, candidates are extracted from a variety of knowledge sources; so far, we experimented with WordNet (Fellbaum, 1998), Microsoft Encarta encyclopedia, Roget, as well as synonym sets generated from bilingual dic- tionaries, but additional knowledge sources can be integrated as well. Second, provided a list of candi- dates, a number of ranking methods are applied in a weighted combination, resulting in a final list of lexical substitutes ranked by their semantic fit with both the input target word and the context. 3 Candidate Extraction Candidates are extracted using several lexical re- sources, which are combined into a larger compre- hensive resource. WordNet: WordNet is a large lexical database of English, with words grouped into synonym sets called synsets. A problem we encountered with this resource is that often times the only candidate in the synset is the target word itself. Thus, to enlarge the set of candidates, we use both the synonyms and the hypernyms of the target word. We also remove the target word from the synset, to ensure that only vi- able candidates are considered. Microsoft Encarta encyclopedia: The Microsoft Encarta is an online encyclopedia and …

Content truncated to 500 words