Hierarchical Semantic-Category-Tree Model for Chinese-English Machine Translation 被引量：1

Hierarchical Semantic-Category-Tree Model for Chinese-English Machine Translation

下载PDF

导出

摘要 We introduce a novel Semantic-CategoryTree(SCT) model to present the semantic structure of a sentence for Chinese-English Machine Translation(MT).We use the SCT model to handle the reordering in a hierarchical structure in which one reordering is dependent on the others.Different from other reordering approaches,we handle the reordering at three levels:sentence level,chunk level,and word level.The chunk-level reordering is dependent on the sentence-level reordering,and the word-level reordering is dependent on the chunk-level reordering.In this paper,we formally describe the SCT model and discuss the translation strategy based on the SCT model.Further,we present an algorithm for analyzing the source language in SCT and transforming the source SCT into the target SCT.We apply the SCT model to a rule-based patent text MT to evaluate the ability of the SCT model.The experimental results show that SCT is efficient in handling the hierarchical reordering operation in MT. We introduce a novel Sermntic-Category- Tree （SCT） model to present the sen-antic structure of a sentence for Chinese-English Machine Translation （MT）. We use the SCT model to handle the reordering in a hierarchical structure in which one reordering is dependent on the others. Different from other reordering approaches, we handle the reordering at three levels： sentence level, chunk level, and word level. The chunk-level reordering is dependent on the sentence-level reordering, and the word-level reordering is dependent on the chunk-level reordering. In this paper, we formally describe the SCT model and discuss the translation strategy based on the SCT model. Further, we present an algorithm for analyzing the source language in SCT and transforming the source SCT into the target SCT. We apply the SCT model to a role-based patent text MT to evaluate the ability of the SCT model. The experimental results show that SCT is efficient in handling the hierarehical reordering operation in MT.

作者 Zhu Xiaojian Jin Yaohong

机构地区 Institute of Chinese Information Processing CPIC-BNU Joint Laboratory of Machine Translation

出处《China Communications》 SCIE CSCD 2012年第12期80-92,共13页 中国通信（英文版）

基金 supported by the National High Technology Research and Development Program of China under Grant No.2012AA011104 the Fundamental Research Funds for the Center Universities

关键词汉英机器翻译语义分类树模型中国 SCT 分层结构算法分析应用模型 reordering SCT MT function word

分类号 TP391.2 [自动化与计算机技术—计算机应用技术] TP311.13 [自动化与计算机技术—计算机软件与理论]

引文网络
相关文献

参考文献19

1KOEHN P, O CH F, MARCU D. Statistical Phrase-Based Translation [C]// Proceedings of the 2003 Conference of the North American Chapter of the Association for Com- putational Linguistics on Human language Technology, 2003: 48-54.
2CHIANG D. A Hierarchical Phrase-Based Model for Statisti- cal Machine Translation [C]// Proceedings of the 43rd An- nual Meeting on Association for Computational Linguistics, 2005:263-270.
3HUANG Liang, CHIANG D. Forest Rescoring: Faster Deco- ding with Integrated Language Models [C]// Proceedings of the 45rd Annual Meeting on Association for Computational Linguistics, 2007: 144-151.
4AULI M, LOPEZ A, HOANG H, etal. A Systematic Analy- sis of Translation Model Search Spaces [C]// Proceedings of the 4th Workshop on Statistical Machine Translation, 2009: 224-232.
5DENEEFE S, KNIGHIT K, WANG W, et al. What Can Syn- tax-Based MT Leam from Phrase-Based MT [C]// Proceed- ings of EMNLP-CoNLL, 2007: 755-763.
6LIN Dekang. A Path-Based Transfer Model for Machine Translation [C]// Proceedings of Coling 2004: 625-630.
7QUIRK C, MENEZES A, CHERRY C. Dependency Treelet Translation: Syntactically Informed Phrasal SMT [C]// Pro- ceedings of the 43rd Annual Meeting on Association for Corqoutational Linguistics, 2005: 271-279.
8DING Yuan, PALMER M. Machine Translation Using Prob- abilistic Synchronous Dependency Insertion Cxanmmrs [C]// Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, 2005: 541-548.
9XIONG Deyi, LIU Qun, LIN Shoumn. A Dependency Tree- let String Correspondence Model for Statistical Machine Translation [C]// Proceedings of the 2nd Workshop on Sta- tistical Machine Translation, 2007: 40-47.
10SHEN Libin, XU Jinxi, WEISCHEDEL R. A New String-to- Dependency Machine Translation Algorithm with a Target Dependency Language Model [C]// Proceedings of ACL, 2008: HLT, 577-585.