An Unsupervised Approach to Chinese Word Sense Disambiguation Based on Hownet

Hao Chen ； Ting-Ting He ； Dong-Hong Ji ； Chang-Qin Quan

《中文計算語言學期刊》 10卷4期 (2005/12) Pp. 473-482

https://doi.org/10.30019/IJCLCLP.200512.0005

並列摘要

The research on word sense disambiguation (WSD) has great theoretical and practical significance in many fields of natural language processing (NLP). This paper presents an unsupervised approach to Chinese word sense disambiguation based on Hownet (an electronic Chinese lexical resource). In our approach, contexts that include ambiguous words are converted into vectors by means of a second-order context method, and these context vectors are then clustered by the k-means clustering algorithm. Lastly, the ambiguous words can be disambiguated after a similarity calculation process is completed. Our experiments involved extraction of terms, and an 82.62% average accuracy rate was achieved.

並列關鍵字

Word Sense Disambiguation ； Hownet ； Second-Order Context ； K-Means Clustering

參考文獻

Hownet

Li, F.,B. Xue,Y. L. Huang(2002).A Novel K-means Clustering Based on Initial Central Superior.Computer Science.29(7),94-96.

Li, J. Z.,Ph.D.Thesis(1999).The Research on Chinese Word Sense Disambiguation.

Lu, S.,S. Bai,X. Huang(2002).An Unsupervised Approach to Word Sense Disambiguation Based on Sense-Words in Vector Space Model.Journal of Software.13(6),1082-1089.

MacQueen, J.(1967).Some methods for classification and analysis of multivariate observations.(proceedings of 5th Symp. Math. Statist, Prob).