在实用机器翻译系统的研究开发中,复杂长句的翻译处理是其面临的一个主要难题。本文提出一种多语种通用的基于多策略分析的复杂长句翻译处理算法,该算法通过基于实例模式匹配和规则分析相结合的方法,综合利用源语言句子中多种相关的语言特征,包括语法语义特征、句子长度、标点符号、功能词以及上下文语境条件等对复杂长句进行切分简化处理和译文的复合生成。另一方面,通过对不同语种设计相同的知识表示形式,实现该算法对不同语种翻译系统的通用性。
Abstract
The processing of complex long sentences is a difficult problem in the implementation of a practical machine translation system. In this paper ,a processing approach to the complex long sentence based on multi-strategy is proposed ,in which the rule-based analysis and case-based consistent matching are combined by using various linguistic features ,including sentence length ,punctuation ,functional words and contextual condition and so on ,which is used to segment the complex sentence into several simple sentences and to compose the translation text of these simple sentences together. In addition ,by designing the uniform formalism of the knowledge representation ,it is possible for this approach to be suitable to multi-lingual translation system.
关键词
机器翻译 /
多策略分析 /
长句切分简化处理
{{custom_keyword}} /
Key words
Machine Translation /
hybrid strategy parsing approach /
segmentation processing of complex long sentence
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] R. Chandrasekar ,C. Doran ,B. Srinivas. Motivations and methods for text simplification [Poster paper] . In : Proceedings of the 16th International Conference on Computational Linguistics (COLING’96) . Copenhagen ,Sweden ,1996 ,8 :1041 - 1044
[2] R. Chandrasekar ,B. Srinivas :Automatic induction of rules for text simplification. Knowledge-Based Systems ,1997 ,10 :183 - 190
[3] Mary Flanagan. MT today :Emerging roles ,new successes. Machine Translation ,1997 ,12 :25 - 27
[4] B. Srinivas. Complexity of lexical descriptions : relevance to partial parsing. Doctoral Dissertation Department of Computer and Information Sciences. University of Pennsylvannia. Philadelphia ,PA ,1997
[5] Huang Heyan ,et. al. The Design and Implementation Principle of an Interactive Hybrid Strategies Machine Translation System: IHSMTS ,proceedings of the International conference in Machine Translation & computer language Information processing ,pp. 270 - 276 ,1999. 6 ,Beijing
[6] Huang Heyan , et. al. A Hierarchical Adjustable Taxonomy-based Consistent Unification Algorithm in Rule-based Intelligent System ,The 2nd China-Korea Joint Symposium on Oriental Language Processing , Korea ,1996
[7] 陈肇雄,高庆狮. 智能型英汉机器翻译系统IMT/EC ,中国科学(A辑) ,1989 (2)
[8] Chen ZhaoXiong,“IMT - KB :A Knowledge base System for Machine Translation”,Proc. of the Inter. Conf. For CPCOL ,Torondo ,1988
[9] 贺琛,黄河燕,陈肇雄. 英语文本简化处理方法综述, ICCC2001 ,上海
[10] 黄河燕等. IHSMTS中多策略译文生成算法, ICCC2001 ,上海
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金和杰出青年基金(69925102)
{{custom_fund}}
PDF(251 KB)
