HIT-CIR: An Unsupervised WSD System Based on Domain Most Frequent Sense Estimation

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 407–410, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics HIT-CIR: An Unsupervised WSD System Based on Domain Most Frequent Sense Estimation Yuhang Guo, Wanxiang Che, Wei He, Ting Liu, Sheng Li Harbin Institute of Technolgy Harbin, Heilongjiang, PRC yhguo@ir.hit.edu.cn Abstract This paper presents an unsupervised sys- tem for all-word domain specific word sense disambiguation task. This system tags target word with the most frequent sense which is estimated using a thesaurus and the word distribution information in the domain. The thesaurus is automati- cally constructed from bilingual parallel corpus using paraphrase technique. The recall of this system is 43.5% on SemEval- 2 task 17 English data set. 1 Introduction Tagging polysemous word with its most frequent sense (MFS) is a popular back-off heuristic in word sense disambiguation (WSD) systems when the training data is inadequate. In past evalua- tions, MFS from WordNet performed even bet- ter than most of the unsupervised systems (Snyder and Palmer, 2004; Navigli et al., 2007). MFS is usually obtained from a large scale sense tagged corpus, such as SemCor (Miller et al., 1994). However, some polysemous words have different MFS in different domains. For example, in the Koeling et al. (2005) corpus, target word coach means “manager” mostly in the SPORTS domain but means “bus” mostly in the FINANCE domain. So when the MFS is applied to specific domains, it needs to be re-estimated. McCarthy et al. (2007) proposed an unsuper- vised predominant word sense acquisition method which obtains domain specific MFS without sense tagged corpus. In their method, a thesaurus, in which words are connected with their distribu- tional similarity, is constructed from the domain raw text. Word senses are ranked by their preva- lence score which is calculated using the thesaurus and the sense inventory. In this paper, we propose another way to con- struct the thesaurus. We use statistical machine Figure 1: The architecture of HIT-CIR translation (SMT) techniques to extract paraphrase pairs from bilingual parallel text. In this way, we avoid calculating similarities between every pair of words and could find semantic similar words or compounds which have dissimilar distributions. Our system is comprised of two parts: the word sense ranking part and the word sense tagging part. Senses are ranked according to their prevalence score in the target domain, and the predominant sense is used to tag the occurrences of the target word in the test data. The architecture of this sys- tem is shown in Figure 1. The word sense ranking part includes following steps. 1. Tag the POS of the background text, count the word frequency in each POS, and get the polysemous word list of the POS. 2. Using SMT techniques to extract phrase table 407 Figure 2: Word sense ranking for the noun backbone from the bilingual corpus. Extract the para- phrases (called as neighbor words) with the phrase table for each word in the polysemous word list. 3. Calculate the prevalence …

Content truncated to 500 words