对于汉英机器翻译而言,由于汉语中缺乏与英语冠词相应的语言范畴,而且面向人的冠词用法规则很难满足机器翻译处理的需要,冠词的误用严重地影响了最终译文的质量。本文提出一种将基于转换的错误驱动的学习机制用于冠词处理的策略,初步实验显示,这种方法可以有效地提高机器译文中冠词使用的准确率。
Abstract
Because Chinese language has no corresponding category with English articles and the usage rules of articles oriented to human are difficult to operationalize for machine t ranslation ,there are many cases in using articles incorrectly in Chinese-English machine t ranslation system ,which degrade the quality of the output t ranslation severely. In this paper ,we proposal a st rategy for article selection which based the Transformation-Based Error2Driven Learning Algorithm ,an initial experimental result shows the st rategy can improve the accuracy in using articles.
关键词
机器翻译 /
冠词选择 /
基于转换的错误驱动学习
{{custom_keyword}} /
Key words
Machine Translation /
Article Selection /
Transformation-Based Error-Driven Learning
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1 ] M. Nagao ,A Framework of a Mechanical Translation between Japanese and English by Analogy Principle , in :A. Elithorn et al. eds. , Artificial and Human Intelligence , NATO Pubilcation
[2 ] P. F. Brown et al. , A Statistical Approach to Machine Translation , Computational Linguistics ,Volume 16 ,Number 2 ,1990
[3 ] R. D.Brown et al. ,Applying Statistical English Language Model to Symbolic Machine Translation ,in Proceedings of TMI 95 ,1995
[4 ] 段慧明,俞士汶,关于 1995 年度机器翻译评测的总结报告《, 计算机世界报》评测版 ,1996 年 3 月 25 日
[5 ] L. G.亚历山大《, 朗文英语语法》,外语教学与研究出版社 ,1991 ,pp. 105 - 136
[6 ] K. Knight et al. , Automated Postediting of Documents ,in proceedings of AAAI94 ,1994
[7 ] E. Brill , Transformation - Based Error - Driven Learning and Natural Language Processing :A Case Study in Part-of-Speech Tagging ,Computational Linguistics ,Volume 21 ,Number 4 ,1995
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(318 KB)
