40g机器学习机器学习经典translation techniques in cross-language information retrieval.pdf

Cross-language information retrieval (CLIR) is an active sub- ain of information retrieval (IR). Like IR, CLIR is centred upon the search for documents, and for information con ned within those documents. Unlike IR, CLIR must reconcile queries and documents which are written in different languages. The usual solution to this mismatch involves translating the query and/or the documents before performing the search. Translation is therefore a pivotal activity for CLIR engines. Over the last 15 years, the CLIR community has developed a wide range of techniques and models supporting free text translation. This paper presents an overview of those techniques, with a special emphasis on recent developments. Categories and Subject Descriptors: A.1 [ ]: Introduction and survey; H.3.1 [ ]: Dictionaries; Thesauruses; Linguistic Processing; I.2.7 [ ]: Machine translation; Text Analysis; Language Parsing and Understanding Genera rms: Algorithms, Languages Additional Key Words and Phrases: Cross-language information retrieval, query translation, doc- ument translation, bilingual dictionary, parallel corpora, machine translation, semantic model The World Wide Web is polyglot in nature. It expresses all human languages, it speaks all dialects. By comparison, the erage Web user is often a monoglot, re- stricted to just one native language, or a handful at best. This mismatch places a Author’s address: Dong Zhou, School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, Hunan, China; email: dongzhou1979@. Permission to make digital/ of all or part of this material without fee for personal or classroom use provided that the copies are not made or distributed for profit or commercial advantage, the ACM copyright/server