JAIST: Clustering and Classification Based Approaches for Japanese WSD

Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 379–382, Uppsala, Sweden, 15-16 July 2010. c⃝2010 Association for Computational Linguistics JAIST: Clustering and Classification based Approaches for Japanese WSD Kiyoaki Shirai Makoto Nakamura Japan Advanced Institute of Science and Technology {kshirai,mnakamur}@jaist.ac.jp Abstract This paper reports about our three par- ticipating systems in SemEval-2 Japanese WSD task. The first one is a clustering based method, which chooses a sense for, not individual instances, but automatically constructed clusters of instances. The sec- ond one is a classification method, which is an ordinary SVM classifier with simple domain adaptation techniques. The last is an ensemble of these two systems. Results of the formal run shows the second system is the best. Its precision is 0.7476. 1 Introduction This paper reports about our systemsinSemEval- 2 Japanese Word Sense Disambiguation (WSD) task (Okumura et al., 2010). This task is a lexi- cal sample task for Japanese WSD and has the fol- lowing two characteristics. First, a balanced word- sense tagged corpus is used for the task. Since it consists of sub-corpora of several domains or gen- res, domain adaptation might be required. Second, the task takes into account not only the instances having a sense in the given set but also the in- stances having a sense not found in the set (called ‘new sense’). Participants are required to identify new senses of words in this task. The second characteristics of the task is mainly considered in our system. A clustering based approach is investigated to identify new senses. Our system first constructs a set of clusters of given word instances using unsupervised cluster- ing techniques. This is motivated by the fact that the new sense is not defined in the dictionary, and sense induction without referring to the dictionary would be required. Clusters obtained would be sets of instances having the same sense, and some of them would be new sense instances. Then each cluster is judged whether instances in it have a new sense or not. An ordinary classification-based ap- proach is also considered. That is, WSD classifiers are trained by a supervised learning algorithm. Furthermore, simple techniques considering gen- res of sub-corpora are incorporated into both our clustering and classification based systems. The paper continues as follows, Section 2 de- scribes our three participating systems, JAIST-1, JAIST-2 and JAIST-3. The results of these systems are reported and discussed in Section 3. Finally we conclude the paper in Section 4. 2 Systems 2.1 JAIST-1: Clustering based WSD System JAIST-1 was developed by a clustering based method. The overview of the system is shown in Figure 1. It consists of two procedures: (A) clus- ters of word instances are constructed so that the instances of the same sense are merged, (B) then similarity between a cluster and a sense in a dic- tionary is measured in order to determine senses of instances in each cluster. Corpus 【サービス】 (service) S 客に対するもてなし。接待。 help that people who work in a shop give you S …

Content truncated to 500 words