A Fully Unsupervised Word Sense Disambiguation Method Using Dependency Knowledge

Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the ACL, pages 28–36, Boulder, Colorado, June 2009. c⃝2009 Association for Computational Linguistics A Fully Unsupervised Word Sense Disambiguation Method Using Dependency Knowledge Ping Chen Dept. of Computer and Math. Sciences University of Houston-Downtown chenp@uhd.edu Chris Bowes Dept. of Computer and Math. Sciences University of Houston-Downtown bowesc@uhd.edu Wei Ding Department of Computer Science University of Massachusetts-Boston ding@cs.umb.edu David Brown Dept. of Computer and Math. Sciences University of Houston-Downtown brownd@uhd.edu Abstract Word sense disambiguation is the process of determining which sense of a word is used in a given context. Due to its importance in understanding semantics of natural languages, word sense disambiguation has been exten- sively studied in Computational Linguistics. However, existing methods either are brit- tle and narrowly focus on specific topics or words, or provide only mediocre performance in real-world settings. Broad coverage and disambiguation quality are critical for a word sense disambiguation system. In this paper we present a fully unsupervised word sense dis- ambiguation method that requires only a dic- tionary and unannotated text as input. Such an automatic approach overcomes the problem of brittleness suffered in many existing methods and makes broad-coverage word sense dis- ambiguation feasible in practice. We evalu- ated our approach using SemEval 2007 Task 7 (Coarse-grained English All-words Task), and our system significantly outperformed the best unsupervised system participating in Se- mEval 2007 and achieved the performance ap- proaching top-performing supervised systems. Although our method was only tested with coarse-grained sense disambiguation, it can be directly applied to fine-grained sense disam- biguation. 1 Introduction In many natural languages, a word can represent multiple meanings/senses, and such a word is called a homograph. Word sense disambiguation(WSD) is the process of determining which sense of a ho- mograph is used in a given context. WSD is a long-standing problem in Computational Linguis- tics, and has significant impact in many real-world applications including machine translation, informa- tion extraction, and information retrieval. Gener- ally, WSD methods use the context of a word for its sense disambiguation, and the context informa- tion can come from either annotated/unannotated text or other knowledge resources, such as Word- Net (Fellbaum, 1998), SemCor (SemCor, 2008), Open Mind Word Expert (Chklovski and Mihal- cea, 2002), eXtended WordNet (Moldovan and Rus, 2001), Wikipedia (Mihalcea, 2007), parallel corpora (Ng, Wang, and Chan, 2003). In (Ide and V´eronis, 1998) many different WSD approaches were de- scribed. Usually, WSD techniques can be divided into four categories (Agirre and Edmonds, 2006), • Dictionary and knowledge based methods. These methods use lexical knowledge bases such as dictionaries and thesauri, and hypoth- esize that context knowledge can be extracted from definitions of words. For example, Lesk disambiguated two words by finding the pair of senses with the greatest word overlap in their dictionary definitions (Lesk, 1986). • Supervised methods. Supervised methods mainly adopt context to disambiguate words. A supervised method includes a training phase and a testing phase. In the training phase, a sense-annotated training …

Content truncated to 500 words