HR-WSD: System Description for All-Words Word Sense Disambiguation on a Specific Domain at SemEval-2010

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 433–435, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics HR-WSD: System Description for All-words Word Sense Disambiguation on a Specific Domain at SemEval-2010 Meng-Hsien Shih National Taipei University of Technology Taipei, Taiwan, ROC. simon.xian@gmail.com Abstract The document describes the knowledge- based Domain-WSD system using heuris- tic rules (knowledge-base). This HR- WSD system delivered the best perfor- mance (55.9%) among all Chinese sys- tems in SemEval-2010 Task 17: All-words WSD on a specific domain. 1 Introduction Word Sense Disambiguation (WSD) is essential for language understanding systems such as in- formation retrieval, summarization, and machine translation systems (Dagan and Itai, 1994; Schutze and Pedersen, 1995; Ng and Zelle, 1997). In par- ticular due to the rapid development of other is- sues in computational linguistics, WSD has been considered the next important task to be solved. Among various WSD tasks, the lexical sample task can achieve a precision rate more than 70% in Chinese, so can the all-words task in English, but currently no Chinese all-words WSD system is available. This study proposes an all-words WSD system conducted on a specific domain which can achieve a 55.9% precision rate. This system makes use of certain characteristics of WordNet. First, the sense inventory in Chinese WordNet is ordered by the “prototypicality” of the words. In other words, the first sense of a word with multiple senses will be the prototype mean- ing of that word. In addition to semantic relations and sense definitions, Chinese WordNet also in- cludes sense axes which indicate the relations be- tween Chinese senses and corresponding English senses. 2 Proposed Approach Two heuristic rules are devised to characterize domain texts: In a domain text, domain senses are more likely to occur in words if they have one (Heuristic Rule 1); on the other hand, for words with no domain senses, the most generic usages (prototype senses) are more likely to be adopted (Heuristic Rule 2). Therefore, as proposed by Li et al.(1995) for the WordNet-based domain- independent texts WSD task, two heuristic rules (HR) are taken into consideration in the domain WSD test: for all senses sk of w do if w has domain sense elsechoose domain sense sk choose prototype sense s1 end Figure 1: Heuristic Rules based WSD Besides, sense definitions from WordNet were also tested with simplified Lesk algorithm (Lesk, 1986; Kilgarriff and Rosenzweig, 2000) in another experiment to examine the effect of considering sense definitions in domain WSD: for all senses sk of w do if w has domain sense choose domain sense sk elseif Dk overlaps with C: choose sense sk with Dk that overlaps the most else: choose prototype sense s1 end Figure 2: HR with simplified Lesk Algorithm. Dk is the set of content words occurring in the dic- tionary definition of sense sk. C is the set of con- tent words in the context. 433 3 Procedures Before the test only preprocessing including seg- mentation and parts of …

Content truncated to 500 words