An Algorithm for Automatic Sentence Alignment of English and Chinese Parallel Corpora
Yao Wei-dong · Jisuanji fangzhen · 2009
Bilingual corpus and its automatic alignment are of great significance to the development of computational linguistics. As the key technology during the course of building corpus,bilingual alignment technology has a direct impact on the future work (such as computer-assisted translation) process. Based on the actual situation of Chinese-English bilingual,this paper proposes a new hybrid algorithm for sentence alignment,which is mainly based on the length-based method and combined with the lexicon-based method. Through the pros and cons of two-way alignment,this algorithm further improved the accuracy of the sentence alignment. Finally,by using 100 documents,more than 5,000 English-Chinese bilingual sentences,the algorithm was verified,and from the effects of alignment it can be found that the results are satisfactory,and the algorithm in practical work is feasible.