Using Wikipedia as an External Knowledge Source for Supporting Contextual Disambiguation  

作　　者：Shahida Jabeen Xiaoying Gao Peter Andreae 

机构地区：[1]School of Engineering and Computer Science, Victoria University of Wellington, New Zealand

出　　处：《Journal of Software Engineering and Applications》2012年第12期175-180,共6页软件工程与应用（英文）

摘　　要：Every term has a meaning but there are terms which have multiple meanings. Identifying the correct meaning of a term in a specific context is the goal of Word Sense Disambiguation (WSD) applications. Identifying the correct sense of a term given a limited context is even harder. This research aims at solving the problem of identifying the correct sense of a term given only one term as its context. The main focus of this research is on using Wikipedia as the external knowledge source to decipher the true meaning of each term using a single term as the context. We experimented with the semantically rich Wikipedia senses and hyperlinks for context disambiguation. We also analyzed the effect of sense filtering on context extraction and found it quite effective for contextual disambiguation. Results have shown that disambiguation with filtering works quite well on manually disambiguated dataset with the performance accuracy of 86%.Every term has a meaning but there are terms which have multiple meanings. Identifying the correct meaning of a term in a specific context is the goal of Word Sense Disambiguation (WSD) applications. Identifying the correct sense of a term given a limited context is even harder. This research aims at solving the problem of identifying the correct sense of a term given only one term as its context. The main focus of this research is on using Wikipedia as the external knowledge source to decipher the true meaning of each term using a single term as the context. We experimented with the semantically rich Wikipedia senses and hyperlinks for context disambiguation. We also analyzed the effect of sense filtering on context extraction and found it quite effective for contextual disambiguation. Results have shown that disambiguation with filtering works quite well on manually disambiguated dataset with the performance accuracy of 86%.

关 键 词：CONTEXTUAL DISAMBIGUATION WIKIPEDIA HYPERLINKS SEMANTIC Relatedness 

分 类 号：R73[医药卫生—肿瘤]