Browse wiki

Jump to: navigation, search
Exploring words with semantic correlations from Chinese Wikipedia
Abstract This paper introduces a way of exploring wThis paper introduces a way of exploring words with semantic relations from Chinese Wikipedia documents. A corpus with structured documents is generated from Chinese Wikipedia pages. Then considering of the hyperlinks, text overlaps and word frequencies, word pairs with semantic relations are explored. Words can be self clustered into groups with tight semantic relations. We roughly measure the semantic relatedness with different document based algorithms and analyze the reliability of our measures in comparing experiment.y of our measures in comparing experiment.
Added by wikilit team Added on initial load  +
Collected data time dimension Cross-sectional  +
Comments For research on semantic relations in NLP, Wikipedia could be employed more in future works
Conclusion In this paper, the Chinese Wikipedia pagesIn this paper, the Chinese Wikipedia pages are used for semantic related word searching. Considering of hyper-links, text overlaps and word frequency, 360,304 word pairs with semantic correlations are explored from 54,745 structured documents from Wikipedia. We also roughly measured semantic correlations, analyzed the reliability of our measures. As with similar hierarchical structure, algorithms and applications for WordNet, Hownet may be transplanted toWikipedia. Semantic Relatedness is used to measuring the degree of semantic correlations, not considering of the difference of relation types. By analyzing the properties of different algorithms based on text overlap or information contents, we are hoping to find a reliable way of searching for groups with semantic correlations and compute the semantic relatedness. For research on semantic relations in NLP, Wikipedia could be employed more in future works. Acknowledgements This research has been partially supported by the Ministry of Education, Science, Sports and Culture, Grant-in-Aid for Scientific Research (B), 19300029. Thanks to Associate Professor Suzuki, and Doctor Matsumoto from The University of Tokushima for instructions. University of Tokushima for instructions.
Conference location Beijing +
Data source Experiment responses  + , Wikipedia pages  +
Dates 19-22 +
Doi 10.1007/978-0-387-87685-6 14 +
Google scholar url http://scholar.google.com/scholar?ie=UTF-8&q=%22Exploring%2Bwords%2Bwith%2Bsemantic%2Bcorrelations%2Bfrom%2BChinese%2BWikipedia%22  +
Has author Yun Li + , Kaiyan Huang + , Fuji Ren + , Yixin Zhong +
Has domain Computer science +
Has topic Semantic relatedness +
Month October  +
Peer reviewed Yes  +
Publication type Conference paper  +
Published in 5th IFIP International Conference on Intelligent Information Processing +
Research design Experiment  +
Research questions In this paper, we work on semantic correlaIn this paper, we work on semantic correlation between Chinese words based onWikipedia documents. A corpus with about 50,000 structured documents is generated fromWikipedia pages. Then considering of hyper-links, text overlaps and word frequency, about 300,000 word pairs with semantic correlations are explored from these documents.We roughly measure the degree of semantic correlations and find groups with tight semantic correlations by self clustering. semantic correlations by self clustering.
Revid 10,763  +
Theories Undetermined
Theory type Analysis  +
Title Exploring words with semantic correlations from Chinese Wikipedia
Unit of analysis Article  +
Url http://www.springerlink.com/content/d11702t4503n2678/  +
Wikipedia coverage Sample data  +
Wikipedia data extraction Live Wikipedia  +
Wikipedia language Chinese  +
Wikipedia page type Article  +
Year 2008  +
Creation dateThis property is a special property in this wiki. 15 March 2012 20:27:55  +
Categories Semantic relatedness  + , Computer science  + , Publications  +
Modification dateThis property is a special property in this wiki. 30 January 2014 20:27:30  +
hide properties that link here 
  No properties link to this page.
 

 

Enter the name of the page to start browsing from.