Research on unsupervised word sense disambiguation

Abstract

The goal of this paper is to give a brief summary of the current unsupervised word sense disambiguation techniques in order to facilitate future research. First of all, the significance of unsupervised word sense disambiguation study is introduced. Then, key techniques of various unsupervised word sense disambiguation studies at home and abroad are reviewed, including data sources, disambiguation methods, evaluation system and the achieved performance. Finally, 14 novel unsupervised word sense disambiguation methods are summarized, and the existing research and possible direction for the development of unsupervised word sense disambiguation study are pointed out. © by Institute of Software, the Chinese Academy of Sciences. All rights reserved.