Study on Sentence Alignment Technology of Chinese-Uygur Kazak Kirgiz Bilingual Corpus Processing and Programming System
Aishan Wumaier · Computer Knowledge and Technology · 2011
In the research and development of natural language,bilingual parallel corpus show their impact gradually.The construction of the parallel corpus is valuable and beneficial for machine translation,bilingual dictionary compilation,meaning disambiguation and crossing-language information retrieval.As a result,the author designs the bilingual corpus processing system,which is very efficient and practical for the switch from Chinese to Uygur,Uygur to Kazak and Kazak to Kirgiz.This processing system blends the technology for document alignment,sentence alignment and word alignment together,which makes it efficient,convenient,speedily and extending.The thesis focus-es on the technology for sentence alignment.