Advertisement

Better Addressing Word Deletion for Statistical Machine Translation

  • Qiang LiEmail author
  • Dongdong Zhang
  • Mu Li
  • Tong Xiao
  • Jingbo Zhu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10102)

Abstract

Word deletion (WD) problems have a critical impact on the adequacy of translation and can lead to poor comprehension of lexical meaning in the translation result. This paper studies how the word deletion problem can be handled in statistical machine translation (SMT) in detail. We classify this problem into desired and undesired word deletion based on spurious and meaningful words. Consequently, we propose four effective models to handle undesired word deletion. To evaluate word deletion problems, we develop an automatic evaluation metric that highly correlates with human judgement. Translation systems are simultaneously tuned for the proposed evaluation metric and BLEU using minimum error rate training (MERT). The experimental results demonstrate that our methods achieve significant improvements in word deletion problems on Chinese-to-English translation tasks.

Keywords

Machine translation Word deletion Automatic evaluation 

Notes

Acknowledgements

This work was done while the first author was visiting the machine translation group at Microsoft Research Asia, and was mainly supported by the Fundamental Research Funds for the Central Universities under Grant No. N140406003, the China Scholarship Council, and the National Natural Science Foundation of China under Grant No. 61272376, No. 61300097 and No. 61432013.

References

  1. 1.
    Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of ACL, pp. 311–318 (2002)Google Scholar
  2. 2.
    Vilar, D., Xu, J., d’Haro, L.F., Ney, H.: Error analysis of statistical machine translation output. In: Proceedings of LREC, pp. 697–702 (2006)Google Scholar
  3. 3.
    Chiang, D.: Hierarchical phrase-based translation. Comput. Linguist. 33(2), 201–228 (2007)CrossRefzbMATHGoogle Scholar
  4. 4.
    Galley, M., Hopkins, M., Knight, K., Marcu, D.: What’s in a translation rule? In: Proceedings of HLT-NAACL, pp. 273–280 (2004)Google Scholar
  5. 5.
    Koehn, P., Schroeder, J.: Experiments in domain adaptation for statistical machine translation. In: Proceedings of the Second Workshop on Statistical Machine Translation, pp. 224–227 (2007)Google Scholar
  6. 6.
    Li, C.H., Zhang, D., Li, M., Zhou, M., Zhang, H.: An empirical study in source word deletion for phrase-based statistical machine translation. In: Proceedings of the Third Workshop on Statistical Machine Translation, pp. 1–8 (2008)Google Scholar
  7. 7.
    Och, F.J., Ney, H.: Discriminative training and maximum entropy models for statistical machine translation. In: Proceedings of ACL, pp. 295–302 (2002)Google Scholar
  8. 8.
    Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pp. 65–72 (2005)Google Scholar
  9. 9.
    Och, F.J.: Minimum error rate training in statistical machine translation. In: Proceedings of ACL, pp. 160–167 (2003)Google Scholar
  10. 10.
    Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proceedings of HLT-NAACL, pp. 48–54 (2003)Google Scholar
  11. 11.
    Zhang, Y., Matusov, E., Ney, H.: Are unaligned words important for machine translation? In: Proceedings of EAMT, pp. 226–233 (2009)Google Scholar
  12. 12.
    Xiao, T., Zhu, J., Zhang, H., Li, Q.: NiuTrans: an open source toolkit for phrase-based and syntax-based machine translation. In: Proceedings of ACL 2012 System Demostrations, pp. 19–24 (2012)Google Scholar
  13. 13.
    Xiong, D., Liu, Q., Lin, S.: Maximum entropy based phrase reordering model for statistical machine translation. In: Proceedings of ACL, pp. 521–528 (2006)Google Scholar
  14. 14.
    Huang, L., Chiang, D.: Forest rescoring: faster decoding with integrated language models. In: Proceedings of ACL, pp. 144–151 (2007)Google Scholar
  15. 15.
    Och, F.J., Ney, H.: Improved statistical alignment models. In: Proceedings of ACL, pp. 440–447 (2000)Google Scholar
  16. 16.
    Menezes, A., Quirk, C.: Syntactic models for structural word insertion and deletion. In: Proceedings of EMNLP, pp. 735–744 (2008)Google Scholar
  17. 17.
    Hermjakob, U.: Improved word alignment with statistics and linguistic heuristics. In: Proceedings of EMNLP, pp. 229–237 (2009)Google Scholar
  18. 18.
    Zhu, J., Li, Q., Xiao, T.: Improving syntactic rule extraction through deleting spurious links with translation span alignment. Nat. Lang. Eng. 21(2), 227–249 (2015)CrossRefGoogle Scholar
  19. 19.
    Liu, Y., Liu, Q., Lin, S.: Discriminative word alignment by linear modeling. Comput. Linguist. 36(3), 303–339 (2010)CrossRefGoogle Scholar
  20. 20.
    Deng, Y., Zhou, B.: Optimizing word alignment combination for phrase table training. In: Proceedings of ACL-IJCNLP, pp. 229–232 (2009)Google Scholar
  21. 21.
    Parton, K., Habash, N., McKeown, K., Iglesias, G., de Gispert, A.: Can automatic post-editing make MT more meaningful? In: Proceedings of EAMT, pp. 111–118 (2012)Google Scholar
  22. 22.
    Huck, M., Ney, H.: Insertion and deletion models for statistical machine translation. In: Proceedings of HLT-NAACL, pp. 347–351 (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Qiang Li
    • 1
    Email author
  • Dongdong Zhang
    • 2
  • Mu Li
    • 2
  • Tong Xiao
    • 1
  • Jingbo Zhu
    • 1
  1. 1.Northeastern UniversityShenyangChina
  2. 2.Microsoft Research AsiaBeijingChina

Personalised recommendations