Browse wiki

Jump to: navigation, search
Automatic word sense disambiguation based on document networks
Abstract In this paper, a survey of works on word sIn this paper, a survey of works on word sense disambiguation is presented, and the method used in the Texterra system [1] is described. The method is based on calculation of semantic relatedness of Wikipedia concepts. Comparison of the proposed method and the existing word sense disambiguation methods on various document collections is given. on various document collections is given.
Added by wikilit team Added on initial load  +
Collected data time dimension Cross-sectional  +
Conclusion In the paper, a word sense disambiguation In the paper, a word sense disambiguation method based on document networks is described. The advan tages of the method are as follows: • coverage of a large portion of the natural lan guage, • easiness of understanding reasons for selecting a particular sense, • large coverage of possible senses (for the senses, both dictionary terms and cases of term use in texts are used), • the method is completely automatic. The disadvantage of the method is that preliminary processing of Wikipedia is required. Our experiments showed that accuracy of the method is comparable with that of systems described in the literature. Taking into account link types makes it possible to better calculate semantic relatedness between the terms, which is evidenced by the improve ment of accuracy and recall of the word sense disam biguation method. Moreover, the method was tested on different collections, which yields a more complete picture of results of the algorithm operation. The paper also discusses difficulties of comparison of the existing algorithms, which are due to the fact that the commonly accepted collection of test docu ments SenseEval is not suitable for comparing Wikipe dia based methods. An escape of this situation might be creation and support of a similar corpus on the basis of Wikipedia and adaptation of the existing methods to testing on such a collection.g methods to testing on such a collection.
Data source Experiment responses  + , Wikipedia pages  +
Doi 10.1134/S0361768810010032 +
Google scholar url http://scholar.google.com/scholar?ie=UTF-8&q=%22Automatic%2Bword%2Bsense%2Bdisambiguation%2Bbased%2Bon%2Bdocument%2Bnetworks%22  +
Has author Denis Turdakov + , S.D. Kuznetsov +
Has domain Computer science +
Has topic Computational linguistics +
Issue 1  +
Peer reviewed Yes  +
Publication type Journal article  +
Published in Programming and Computer Software +
Research design Experiment  +
Research questions In this paper, a survey of works on word sIn this paper, a survey of works on word sense disambiguation is presented, and the method used in the Texterra system [1] is described. The method is based on calculation of semantic relatedness of Wiki pedia concepts. Comparison of the proposed method and the existing word sense disambiguation methods on various document collections is given. on various document collections is given.
Revid 10,672  +
Theories Undetermined
Theory type Analysis  +
Title Automatic word sense disambiguation based on document networks
Unit of analysis N/A  +
Url http://dx.doi.org/10.1134/S0361768810010032  +
Volume 36  +
Wikipedia coverage Case  +
Wikipedia data extraction Dump  +
Wikipedia language Not specified  +
Wikipedia page type Article  +
Year 2010  +
Creation dateThis property is a special property in this wiki. 15 March 2012 20:24:08  +
Categories Computational linguistics  + , Computer science  + , Publications with missing comments  + , Publications  +
Modification dateThis property is a special property in this wiki. 30 January 2014 20:20:46  +
hide properties that link here 
  No properties link to this page.
 

 

Enter the name of the page to start browsing from.