DFKI-LT - Integrating Different Strategies in Cross-Language Information Retrieval in the MIETTA Project

Paul Buitelaar, Klaus Netter, Feiyu Xu
Integrating Different Strategies in Cross-Language Information Retrieval in the MIETTA Project
3 Proceedings of the 14th Twente Workshop on Language Technology (TWLT 14). Language Technology in Multimedia Information Retrieval, December 7-8, Pages 9-17, o.A., Enschede, The Netherlands, 1998
 
In this paper we describe an integrated approach to cross-language retrieval within the MIETTA project, whose objective is to build a special purpose search engine in the tourism domain that covers information from a number of geographical regions. MIETTA is designed to enable users to search and retrievegeographical regions. MIETTA is designed to enable users to search and retrieve information on the regions covered in their own language preferably. In order to facilitate the user with such functionality, the system includes document translation, cross-language query translation, multilingual generation from information extraction templates and document classification. In addition, query expansion is offered to identify proper query translation and enable template matching for information extraction purposes.
 
Files: BibTeX, Buitelaar:1998:IDS.pdf