Cross-language information retrieval: Difference between revisions

Revision as of 15:50, 22 August 2016

Revision as of 01:58, 19 April 2017

Line 1:

{{refimprove|date=September 2014}}

'''Cross-language information retrieval (CLIR)''' is a subfield of [[information retrieval]] dealing with retrieving information written in a language different from the language of the user's query.<ref>Wang, Jianqiang, and Douglas W. Oard. "Matching meaning for cross-language information retrieval." ''Information Processing & Management''48.4 (2012): 631-53. </ref> For example, a user may pose their query in English but retrieve relevant documents written in French. To do so, most of CLIR systems use translation techniques.<ref>"[https://www.academia.edu/2475776/Versatile_question_answering_systems_seeing_in_synthesis Versatile question answering systems: seeing in synthesis]", Mittal et al., IJIIDS, 5(2), 119-142, 2011.</ref> CLIR techniques can be classified into different categories based on different translation resources:<ref>Thai, Perishan."An Introduction to Cross-Language Information Retrieval Approaches". Web. Web.simmons.edu</ref>

* Dictionary-based CLIR techniques

* Parallel corpora based CLIR techniques

Line 7:

* Machine translator based CLIR techniques

The first workshop on CLIR was held in Zürich during the SIGIR-96 conference.<ref>The proceedings of this workshop can be found in the book ''Cross-Language Information Retrieval'' (Grefenstette, ed; Kluwer, 1998) ISBN 0-7923-8122-X.</ref> Workshops have been held yearly since 2000 at the meetings of the [[Cross Language Evaluation Forum]] (CLEF). Researchers also convene at the annual [[Text Retrieval Conference]] (TREC) to discuss their findings regarding different systems and methods of information retrieval, and the conference has served as a point of reference for the CLIR subfield.<ref>Olvera-Lobo, María-Dolores. "Cross-Language Information Retrieval on the Web." ''Handbook of Research on Social Dimensions of Semantic Technologies and Web Services''(n.d.): 704-19. Web.</ref>

The term "cross-language information retrieval" has many synonyms, of which the following are perhaps the most frequent: cross-lingual information retrieval, translingual information retrieval, multilingual information retrieval. The term "multilingual information retrieval" refers to CLIR in general, but it also has a specific meaning of cross-language information retrieval where a document collection is multilingual.