REALIZING TARGET LANGUAGE GENERATION IN DATA-ORIENTED ENGLISH-CHINESE MACHINE TRANSLATION
This paper presents a kind of target language generation mechanism in Data-Oriented English-Chinese Machine Translation. This mechanism applies the theory of Data-Oriented Parsing used in language analysis traditionally into target language generation equally. Through linearizing the result of source language analysis -- a parse tree, the final translation in target language is generated. To prove the efficiency of the proposed method, the knowledge source is constructed based on the real-world English corpus, and the other real-world English corpus is used as the test set. The experiment result shows that the quality of translation in target language is satisfactory.
Data-Oriented Parsing target language generation treebank fragment bank fragment-combination-form bank generation-fragment-combination-form
TAO ZHANG RUI FENG YUE-JIE ZHANG
School of Information Management & Engineering, Shanghai University of Finance & Economics, Shanghai Department of Computer Science & Engineering, Shanghai Key Laboratory of Intelligent Information Pro
国际会议
2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)
大连
英文
2624-2629
2006-08-13(万方平台首次上网日期,不代表论文的发表时间)