Unsupervised word sense induction using rival penalized competitive learning. (May 2015)

• Record Type: Journal Article
• Authors: Huang, Yanzhou; Shi, Xiaodong; Su, Jinsong; Chen, Yidong; Huang, Guimin
• Is Part Of: Engineering applications of artificial intelligence. Volume 41(2015:May)
• Page Start: 166
• Page End: 174
• Publication Date: 2015-05
• Subjects: Natural language processing -- Word sense induction -- Multi-granularity semantic representation -- Competitive learning; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2015.02.004
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Word sense induction (WSI) aims to automatically identify different senses of an ambiguous word from its contexts. It is a nontrivial task to perform WSI in natural language processing because word sense ambiguity is pervasive in linguistic expressions. In this paper, we construct multi-granularity semantic spaces to learn the representations of ambiguous instances, in order to capture richer semantic knowledge during context modeling. In particular, we not only consider the semantic space of words, but the semantic space of word clusters and topics as well. Moreover, to circumvent the difficulty of selecting the number of word senses, we adapt a rival penalized competitive learning method to determine the number of word senses automatically via gradually repelling the redundant sense clusters. We validate the effectiveness of our method on several public WSI datasets and the results show that our method is able to improve the quality of WSI over several competitive baselines.