UofL: Word Sense Disambiguation Using Lexical Cohesion

Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), pages 476–479, Prague, June 2007. c⃝2007 Association for Computational Linguistics UofL: Word Sense Disambiguation Using Lexical Cohesion Yllias Chali Department of Computer Science University of Lethbridge Lethbridge, Alberta, Canada, T1K 3M4 chali@cs.uleth.ca Shafiq R. Joty Department of Computer Science University of Lethbridge Lethbridge, Alberta, Canada, T1K 3M4 jotys@cs.uleth.ca Abstract One of the main challenges in the applica- tions (i.e.: text summarization, question an- swering, information retrieval, etc.) of Natural Language Processing is to deter- mine which of the several senses of a word is used in a given context. The problem is phrased as “Word Sense Disambiguation (WSD)” in the NLP community. This paper presents the dictionary based disambigua- tion technique that adopts the assumption of one sense per discourse in the context of SemEval-2007 Task 7: “Coarse-grained English all-words”. 1 Introduction Cohesion can be defined as the way certain words or grammatical features of a sentence can connect it to its predecessors (and successors) in a text. (Halliday and Hasan, 1976) defined cohesion as “the set of possibilities that exist in the language for making text hang together”. Cohesion occurs where the interpretation of some element in the discourse is dependent on that of another. For ex- ample, an understanding of the reference of a pro- noun (i.e.: he, she, it, etc.) requires to look back to something that has been said before. Through this cohesion relation, two text clauses are linked to- gether. Cohesion is achieved through the use in the text of semantically related terms, reference, ellipse and conjunctions (Barzilay and Elhadad, 1997). Among the different cohesion-building devices, the most easily identifiable and the most frequent type is lexical cohesion. Lexical cohesion is created by using semantically related words (repetitions, synonyms, hypernyms, hyponyms, meronyms and holonyms, glosses, etc.) Our technique used WordNet (Miller, 1990) as the knowledge source to find the semantic relations among the words in a text. We assign weights to the semantic relations. The technique can be de- composed into two steps: (1) building a representa- tion of all possible senses of the words and (2) dis- ambiguating the words based on the highest score. The remainder of this paper is organized as fol- lows. In the next section, we review previous work. In Section 3, we define the semantic relations and their weights. Section 4 presents our two step pro- cedure for WSD. We conclude with the evaluation. 2 Previous Work Lexical Chaining is the process of connecting se- mantically related words, creating a set of chains that represent different threads of cohesion through the text (Galley and McKeown, 2003). This inter- mediate representation of text has been used in many natural language processing applications, including automatic summarization (Barzilay and Elhadad, 1997; Silber and McCoy, 2003), informa- tion retrieval (Al-Halimi and Kazman, 1998), and intelligent spell checking (Hirst and St-Onge, 1998). Morris and Hirst (1991) at first proposed a man- ual method for computing lexical chains and first computational model of lexical chains …

Content truncated to 500 words