You are in:Home/Publications/Can Wikipedia Be A Reliable Source For Translation?Testing Wikipedia Cross Lingual Coverage of Medical Domain

Prof. Mohamed Abd El-Fattah Mohamed Hamed Awad :: Publications:

Title:
Can Wikipedia Be A Reliable Source For Translation?Testing Wikipedia Cross Lingual Coverage of Medical Domain
Authors: Eslam Amer1, Mohamed Abd-Elfattah
Year: 2016
Keywords: Not Available
Journal: IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661,p-ISSN: 2278-8727, Volume 18, Issue 3, Ver. II (May-Jun. 2016), PP 16-22 www.iosrjournals.org
Volume: IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661,p-ISSN: 2278-8727, Volume 18, Issue 3, Ver. II (May-Jun. 2016), PP 16-22 www.iosrjournals.org
Issue: Not Available
Pages: Not Available
Publisher: Not Available
Local/International: International
Paper Link: Not Available
Full paper Not Available
Supplementary materials Not Available
Abstract:

This paper introduces Wiki-Transpose, a query translation system for cross-lingual information retrieval (CLIR). Wiki-Transpose rely only on Wikipedia as information source for translations. The main goal of this paper is to check the coverage ratio of Wikipedia against specializedqueries that are related to medical domain. Wiki-Transpose was evaluated using bothEnglish and Portuguese medical queries. Queries are mapped into both English and Portuguese Wikipedia concepts. Experiments showed that Wikipedia coverage ratio of queries is inversely proportional to the query size. Wikipedia coverage of single English term query is about 81%, and 80% for single Portuguese term query. This ratio is decreased when the number of terms in query increased. However in the case of query translation, Wikipedia showed a comparative performance for (English – Portuguese) and (Portuguese – English) translation. In English – Portuguese translation, Wikipedia showed coverage ratio around 60% for single term queries, compared to 88% for Portuguese – English single term queries. The translation coverage ratio is also decreased when number of terms in query increase

Google ScholarAcdemia.eduResearch GateLinkedinFacebookTwitterGoogle PlusYoutubeWordpressInstagramMendeleyZoteroEvernoteORCIDScopus