Applying Machine Translation to Two-Stage Cross-Language Information Retrieval

Simple item page
dc.creatorFujii, Atsushi
dc.creatorIshikawa, Tetsuya
dc.date2000-11-02
dc.date.accessioned2026-07-07T03:16:40Z
dc.date.available2026-07-07T03:16:40Z
dc.descriptionCross-language information retrieval (CLIR), where queries and documents are in different languages, needs a translation of queries and/or documents, so as to standardize both of them into a common representation. For this purpose, the use of machine translation is an effective approach. However, computational cost is prohibitive in translating large-scale document collections. To resolve this problem, we propose a two-stage CLIR method. First, we translate a given query into the document language, and retrieve a limited number of foreign documents. Second, we machine translate only those documents into the user language, and re-rank them based on the translation result. We also show the effectiveness of our method by way of experiments using Japanese queries and English technical documents.
dc.description13 pages, 1 Postscript figure
dc.identifierhttps://arxiv.org/abs/cs/0011003
dc.identifierhttp://arxiv.org/abs/cs/0011003
dc.identifierProceedings of the 4th Conference of the Association for Machine Translation in the Americas (AMTA-2000), pp.13-24, Oct. 2000
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30443
dc.subjectComputation and Language
dc.subjectI.2.7; H.3.3
dc.titleApplying Machine Translation to Two-Stage Cross-Language Information Retrieval
dc.typetext

Files

Collections

arXiv