Chinese Journal of Computers   Full Text
Title	Sense Recognition Research of Hyponymy Based on Concept Space
Authors	LIU Lei1) CAO Cun-Gen2) ZHANG Chun-Xia3) TIAN Guo-Gang2)
Address	1)(College of Applied Sciences, Beijing University of Technology, Beijing 100124) 2)(Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190) 3)(School of Computer Software, Beijing Institute of Technology, Beijing 100081)
Year	2009
Issue	No.8(1651—1661)
Abstract &   Background	Abstract For the polysemy of hyponymy in the phase of building taxonomic hierarchy, this paper presents a method of sense recognition of hyponymy based on concept space. The problem of sense recognition of single concept is transformed into recognition of hyponymy in concept space. Firstly, the contexts of hyponymy are acquired iteratively using coordinate relation patterns. Secondly CiLin and the weight of feature words are used to construct a hyponymy-word vector space. Then LSA is used to reduce the dimension of the vector space. In the final phase, the senses of hyponymy can be recognized using average-group clustering. The relation of decreasing degree of similarity and threshold of clustering, and the effect of CiLin and LSA in experiment are analyzed. Experimental results show that the method is adequate of partitioning the senses the hyponymy. Keywords knowledge acquisition; hyponymy relation; latent semantic analysis; relation acquisition; concept space; sense clustering Background KAT(Knowledge Acquisition from Text) is an important approach of large-scale knowledge acquisition at present. Especially, automatic acquisition of concepts and semantic relations from text has received much attention in the last ten years. The authors’ research interests include the acquisition of concept, relation and attribute in KAT. Relation acquisition focuses on three basic semantic relations (hyponymy, whole-part relation, and co-referent relations). The authors have designed and developed a prototype system of acquiring knowledge from semi-structure text, and use it to acquire specialize knowledge from large-scale Chinese corpus. Research on hyponymy acquisition and verification is a basic and crucial problem in KAT. Hyponymy relations play a crucial role in various NLP(Natural Language Processing) systems, such as systems for information extraction, information retrieval, and dialog systems. Hyponymy relations are also important in accuracy verification of ontologies, knowledge bases and lexicons. The problem of polysemy hinders the building taxonomic hierarchy using hyponymy seriously. Furthermore, it hinders knowledge whole verification and knowledge database.