Synonym-Based Reordering Model for Statistical Machine Translation

详细信息    查看全文

• 关键词：Synonym ; Reordering ; Statistical machine translation ; Feature function
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9773
• 期：1
• 页码：369-378
• 全文大小：338 KB
• 参考文献：1.Tu, M., Zhou, Y., Zong, C.: Exploring diverse features for statistical machine translation model pruning. IEEE/ACM Trans. Audio Speech Lang Process. 23(11), 1847–1857 (2015)CrossRef
  2.Farzi, S., Faili, H., Khadivi, S.: A syntactically informed reordering model for statistical machine translation. J. Exp. Theor. Artif. Intell. 27(4), 449–469 (2015)CrossRef
  3.Tillmann, C.: A unigram orientation model for statistical machine translation. In: HLT-NAACL 2004: Short Papers, pp. 101–104. Association for Computational Linguistics (2004)
  4.Koehn, P., Hoang, H., Birch, A., et al: Moses: open source toolkit for statistical machine translation. In: ACL, pp. 177–180. Association for Computational Linguistics (2007)
  5.Galley, M., Manning, C.D.: A simple and effective hierarchical phrase reordering model. In: EMNLP, pp. 848–856. Association for Computational Linguistics (2008)
  6.Ling, W., Luis, T., Graa, J., Coheur, L., Trancoso, I.: Reordering modeling using weighted alignment matrices. In: ACL-HLT, pp. 450–454. Association for Computational Linguistics (2011)
  7.Yeon-Soo, L.E.E.: Utilizing global syntactic tree features for phrase reordering. IEICE Trans. Inf. Syst. 97(6), 1694–1698 (2014)
  8.Chen, L., Li, M., He, M., Liu, H.: Dependency parsing on source language with reordering information in SMT. In: IALP, pp. 133–136 (2012)
  9.Liang, F., Chen, L., Li, M.: Nasun-urtu: a rule-based source-side reordering on phrase structure subtrees. In: IALP, pp. 173–176 (2011)
  10.Cai, J., Utiyama, M., Sumita, E., et al.: Dependency-based pre-ordering for Chinese-English machine translation. In: ACL, pp. 155–160. Association for Computational Linguistics (2014)
  11.Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: NAACL-HLT, pp. 48–54. Association for Computational Linguistics (2003)
  12.Och, F.J.: Minimum error rate training in statistical machine translation. In: ACL, pp. 160–167. Association for Computational Linguistics (2003)
  13.Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: ACL, pp. 311–318. Association for Computational Linguistics (2002)
  14.Zhang, J., Zhai, F., Zong, C.: A substitution-translation-restoration framework for handling unknown words in statistical machine translation. J. Comput. Sci. Technol. 28(5), 907–918 (2013)CrossRef
  15.Hoang, H., Koehn, P.: Improving mid-range reordering using templates of factors. In: EMNLP, pp. 372–379. Association for Computational Linguistics (2009)
  16.Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. In: ACL, pp. 310–318. Association for Computational Linguistics (1996)
  17.Levy, R., Manning, C.: Is it harder to parse Chinese, or the Chinese treebank? In: ACL, pp. 439–446. Association for Computational Linguistics (2003)
  18.Xiong, D., Liu, Q., Lin, S.: Maximum entropy based phrase reordering model for statistical machine translation. In: ACL, pp. 521–528. Association for Computational Linguistics (2006)
  19.He, Z., Meng, Y., Yu, H.: Maximum entropy based phrase reordering for hierarchical phrase-based translation. In: EMNLP, pp. 555–563. Association for Computational Linguistics (2010)
  20.Ling, W., Graça, J., de Matos, D.M., Trancoso, I., Black, A.W.: Discriminative phrase-based lexicalized reordering models using weighted reordering graphs. In: IJCNLP, pp. 47–55. Association for Computational Linguistics (2011)
  21.Yang, Z., Li, M., Zhu, Z., et al.: A maximum entropy based reordering model for Mongolian-Chinese SMT with morphological information. In: IALP, pp.175–178 (2014)
  22.Yang, N., Li, M., Zhang, D., Yu, N.: A ranking-based approach to word reordering for statistical machine translation. In: ACL, pp. 912–920. Association for Computational Linguistics (2012)
  23.Visweswariah, K., Navratil, J., Sorensen, J., et al.: Syntax based reordering with automatically derived rules for improved statistical machine translation. In: ICCL, pp. 1119–1127 (2010)
  
• 作者单位：Zhenxin Yang (16) (17)
  Miao Li (16)
  Lei Chen (16)
  Kai Sun (17)
  
  16. Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, 230031, China
  17. University of Science and Technology of China, Hefei, 230026, China
  
• 丛书名：Intelligent Computing Methodologies
• ISBN：978-3-319-42297-8
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9773

文摘

Reordering model is the crucial component in statistical machine translation (SMT), since it plays an important role in the generation of fluent translation results. However, the data sparseness is the key factor that greatly affects the performance of reordering model in SMT. In this paper, we exploit synonymous information to alleviate the data sparseness and take Chinese-Mongolian SMT as example. First, a synonym-based reordering model with Chinese synonym is proposed for Chinese-Mongolian SMT. Then, we flexibly integrate synonym-based reordering model into baseline SMT as additional feature functions. Besides, we present source-side reordering as the pre-processing module to verify the extensibility of our synonym-based reordering model. Experiments on the Chinese-Mongolian dataset show that our synonym-based reordering model achieves significant improvement over baseline SMT system.