Browse wiki

Jump to: navigation, search
Web-based pattern learning for named entity translation in Korean-Chinese cross-language information retrieval
Abstract Named entity (NE) translation plays an impNamed entity (NE) translation plays an important role in many applications, such as information retrieval and machine translation. In this paper, we focus on translating NEs from Korean to Chinese in order to improve Korean-Chinese cross-language information retrieval (KCIR). The ideographic nature of Chinese makes NE translation difficult because one syllable may map to several Chinese characters. We propose a hybrid NE translation system. First, we integrate two online databases to extend the coverage of our bilingual dictionaries. We use Wikipedia as a translation tool based on the inter-language links between the Korean edition and the Chinese or English editions. We also use Naver.com's people search engine to find a query name's Chinese or English translation. The second component of our system is able to learn Korean-Chinese (K-C), Korean-English (K-E), and English-Chinese (E-C) translation patterns from the web. These patterns can be used to extract K-C, K-E and E-C pairs from Google snippets. We found KCIR performance using this hybrid configuration over five times better than that a dictionary-based configuration using only Naver people search. Mean average precision was as high as 0.3385 and recall reached 0.7578. Our method can handle Chinese, Japanese, Korean, and non-CJK NE translation and improve performance of KCIR substantially.improve performance of KCIR substantially.
Added by wikilit team Added on initial load  +
Collected data time dimension Cross-sectional  +
Comments We found KCIR performance using this hybrid configuration over five times better than that a dictionary-based configuration using only Naver people search.
Conclusion We found KCIR performance using this hybriWe found KCIR performance using this hybrid configuration over five times better than that a dictionary-based configuration using only Naver people search. Mean average precision was as high as 0.3385 and recall reached 0.7578. Our method can handle Chinese, Japanese, Korean, and non-CJK NE translation and improve performance of KCIR substantially.improve performance of KCIR substantially.
Data source Documents  + , Experiment responses  + , Wikipedia pages  +
Doi 10.1016/j.eswa.2008.02.067 +
Google scholar url http://scholar.google.com/scholar?ie=UTF-8&q=%22Web-based%2Bpattern%2Blearning%2Bfor%2Bnamed%2Bentity%2Btranslation%2Bin%2BKorean-Chinese%2Bcross-language%2Binformation%2Bretrieval%22  +
Has author Yu-Chun Wang + , Richard Tzong-Han Tsai + , Wen-Lian Hsu +
Has domain Computer science +
Has topic Cross-language information retrieval +
Pages 3990-3995  +
Peer reviewed Yes  +
Publication type Journal article  +
Published in Expert Systems with Applications +
Research design Experiment  +
Research questions Named entity (NE) translation plays an impNamed entity (NE) translation plays an important role in many applications, such as information retrieval and machine translation. In this paper, we focus on translating NEs from Korean to Chinese in order to improve Korean–Chinese cross-language information retrieval (KCIR). The ideographic nature of Chinese makes NE translation difficult because one syllable may map to several Chinese characters. We propose a hybrid NE translation system.We propose a hybrid NE translation system.
Revid 11,039  +
Theories Undetermined
Theory type Design and action  +
Title Web-based pattern learning for named entity translation in Korean-Chinese cross-language information retrieval
Unit of analysis Article  +
Url http://dx.doi.org/10.1016/j.eswa.2008.02.067  +
Volume 36  +
Wikipedia coverage Other  +
Wikipedia data extraction Live Wikipedia  +
Wikipedia language Chinese  + , English  + , Korean  +
Wikipedia page type Article  +
Year 2009  +
Creation dateThis property is a special property in this wiki. 15 March 2012 20:32:56  +
Categories Cross-language information retrieval  + , Computer science  + , Publications  +
Modification dateThis property is a special property in this wiki. 30 January 2014 20:32:21  +
hide properties that link here 
  No properties link to this page.
 

 

Enter the name of the page to start browsing from.