Generalized Biwords for Bitext Compression and Translation Spotting:Extended Abstract

摘要

1 IntroductionThe increasing availability of large collections of bilingualparallel corpora has fostered the development of naturallanguageprocessing applications that address bilingual tasks,such as corpus-based machine translation,the automaticextraction of bilingual lexicons,and translation spotting[Simard,2003].A bilingual parallel corpus,or bitext,is atextual collection that contains pairs of documents which aretranslations of one another.In the words of Melamed [2001,p.1],'bitexts are one of the richest sources of linguisticknowledge because the translation of a text into another languagecan be viewed as a detailed annotation of what that textmeans'.