An Equivalent Pseudoword Solution to Chinese Word Sense Disambiguation

Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL, pages 457–464, Sydney, July 2006. c⃝2006 Association for Computational Linguistics An Equivalent Pseudoword Solution to Chinese Word Sense Disambiguation Zhimao Lu+ Haifeng Wang++ Jianmin Yao+++ Ting Liu+ Sheng Li+ + Information Retrieval Laboratory, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China {lzm, tliu, lisheng}@ir-lab.org ++ Toshiba (China) Research and Development Center 5/F., Tower W2, Oriental Plaza, No. 1, East Chang An Ave., Beijing, 100738, China wanghaifeng@rdc.toshiba.com.cn +++ School of Computer Science and Technology Soochow University, Suzhou, 215006, China jyao@suda.edu.cn Abstract This paper presents a new approach based on Equivalent Pseudowords (EPs) to tackle Word Sense Disambiguation (WSD) in Chinese language. EPs are par- ticular artificial ambiguous words, which can be used to realize unsupervised WSD. A Bayesian classifier is implemented to test the efficacy of the EP solution on Senseval-3 Chinese test set. The per- formance is better than state-of-the-art results with an average F-measure of 0.80. The experiment verifies the value of EP for unsupervised WSD. 1 Introduction Word sense disambiguation (WSD) has been a hot topic in natural language processing, which is to determine the sense of an ambiguous word in a specific context. It is an important technique for applications such as information retrieval, text mining, machine translation, text classifica- tion, automatic text summarization, and so on. Statistical solutions to WSD acquire linguistic knowledge from the training corpus using ma- chine learning technologies, and apply the knowledge to disambiguation. The first statistical model of WSD was built by Brown et al. (1991). Since then, most machine learning methods have been applied to WSD, including decision tree, Bayesian model, neural network, SVM, maxi- mum entropy, genetic algorithms, and so on. For different learning methods, supervised methods usually achieve good performance at a cost of human tagging of training corpus. The precision improves with larger size of training corpus. Compared with supervised methods, unsuper- vised methods do not require tagged corpus, but the precision is usually lower than that of the supervised methods. Thus, knowledge acquisi- tion is critical to WSD methods. This paper proposes an unsupervised method based on equivalent pseudowords, which ac- quires WSD knowledge from raw corpus. This method first determines equivalent pseudowords for each ambiguous word, and then uses the equivalent pseudowords to replace the ambigu- ous word in the corpus. The advantage of this method is that it does not need parallel corpus or seed corpus for training. Thus, it can use a large- scale monolingual corpus for training to solve the data-sparseness problem. Experimental re- sults show that our unsupervised method per- forms better than the supervised method. The remainder of the paper is organized as fol- lows. Section 2 summarizes the related work. Section 3 describes the conception of Equivalent Pseudoword. Section 4 describes EP-based Un- supervised WSD Method and the evaluation re- sult. The last section concludes our approach. 2 Related Work For supervised WSD methods, a knowledge ac- quisition …

Content truncated to 500 words