Integrate Syntactic Information into Chinese Word Sense Disambiguation Technology

Word sense disambiguation (WSD) is important to many application problems in natural language processing fields. It plays a very important role in information retrieval systems, machine translation systems, text classification systems and automatic summarization systems. Its task is to automatically choose the intended sense of an ambiguous word in a given context. In this paper, a new supervised word sense disambiguation method is proposed, where syntactic information is introduced. The parsing tree of its context including the ambiguous word is built. Then, the parsing tree is traveled and disambiguation features are extracted including parsing information, part of speech information and word information. The bayesian model is used to build word sense disambiguation classifier for every Chinese ambiguous word. Experimental results show that accuracy rate of disambiguation arrives at 60% after the classifier is applied to test data.