Skip to main content
SpringerLink
Log in

I Can Guess What You Mean: A Monolingual Query Enhancement for Machine Translation

  • Conference paper
  • First Online:
Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data (NLP-NABD 2016, CCL 2016)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10035))

  • 1747 Accesses

Abstract

We introduce a monolingual query method with additional webpage data to improve the translation quality for more and more official use requirement of statistical machine translation outputs. The motivation behind this method is that we can improve the readability of sentence once for all if we replace translation sentences with the most related sentences generated by human. Based on vector space representations for translated sentences, we perform a query on search engine for additional reference text data. Then we rank all translation sentences to make necessary replacement from the query results. Various vector representations for sentence, TFIDF, latent semantic indexing, and neural network word embedding, are conducted and the experimental results show an alternative solution to enhance the current machine translation with a performance improvement about 0.5 BLEU in French-to-English task and 0.7 BLEU in English-to-Chinese task.

H. Zhao—This paper was partially supported by Cai Yuanpei Program (CSC No. 201304490199 and No. 201304490171), National Natural Science Foundation of China (No. 61170114 and No. 61272248), National Basic Research Program of China (No. 2013CB329401), Major Basic Research Program of Shanghai Science and Technology Committee (No. 15JC1400103), Art and Science Interdisciplinary Funds of Shanghai Jiao Tong University (No. 14JCRZ04), and Key Project of National Society Science Foundation of China (No. 15-ZDA041).

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    We are aware that there are many other effective method such as [36] who used a parse tree and matrix-vector operations to retain word order information. However, this work is about machine translation sentence processing, we need robust and simple strategy to handle various possible defective sentences.

  2. 2.

    A sophisticated approach is cutting sentence into several relative independent parts according to parse tree of sentence [45, 46], which can be regarded as a further improvement over the current simple segmentation strategy.

References

  1. Huang, S., Chen, H., Dai, X.-Y., Chen, J.: Non-linear learning for statistical machine translation. In: ACL, pp. 825–835 (2015)

    Google Scholar 

  2. Yu, H., Zhu, X.: Recurrent neural network based rule sequence model for statistical machine translation. In: ACL, pp. 132–138 (2015)

    Google Scholar 

  3. Lu, S., Chen, Z., Xu, B.: Learning new semi-supervised deep auto-encoder features for statistical machine translation. In: ACL, pp. 122–132 (2014)

    Google Scholar 

  4. Xiong, D., Zhang, M.: A sense-based translation model for statistical machine translation. In: ACL, pp. 1459–1469 (2014)

    Google Scholar 

  5. Neubig, G., Duh, K.: On the elements of an accurate tree-to-string machine translation system. In: ACL, pp. 143–149 (2014)

    Google Scholar 

  6. Riezler, S., Simianer, P., Haas, C.: Response-based learning for grounded machine translation. In: ACL, pp. 881–891 (2014)

    Google Scholar 

  7. Wang, R., Zhao, H., Lu, B.-L.: Bilingual continuous-space language model growing for statistical machine translation, pp. 1209–1220. IEEE (2015)

    Google Scholar 

  8. Zhang, J., Utiyama, M., Sumita, E., Zhao, H.: Learning local word reorderings for hierarchical phrase-based statistical machine translation. Mach. Transl. 1–18 (2016)

    Google Scholar 

  9. Wang, R., Utiyama, M., Goto, I., Sumita, E., Zhao, H., Lu, B.-L.: Converting continuous-space language models into N-gram language models with efficient bilingual pruning for statistical machine translation. ACM (2016)

    Google Scholar 

  10. Wang, R., Zhao, H., Ploux, S., Lu, B.-L., Utiyama, M.: A Bilingual Graph-Based Semantic Model for Statistical Machine Translation

    Google Scholar 

  11. Zang, S., Zhao, H., Wu, C., Wang, R.: A novel word reordering method for statistical machine translation. In: FSKD, pp. 843–848 (2015)

    Google Scholar 

  12. Zhang, J., Utiyama, M., Sumita, E., Zhao, H.: Learning word reorderings for hierarchical phrase-based statistical machine translation. In: ACL-IJCNLP, pp. 542–548 (2015)

    Google Scholar 

  13. Wang, R., Zhao, H., Lu, B.-L., Utiyama, M., Sumita, E.: Neural network based bilingual language model growing for statistical machine translation. In: EMNLP, pp. 189–195 (2014)

    Google Scholar 

  14. Zhang, J., Utiyama, M., Sumita, E., Zhao, H.: Learning hierarchical translation spans. In: EMNLP, pp. 183–188 (2014)

    Google Scholar 

  15. Wang, R., Utiyama, M., Goto, I., Sumita, E., Zhao, H., Lu, B.-L.: Converting continuous-space language models into N-gram language models for statistical machine translation. In: EMNLP, pp. 845–850 (2013)

    Google Scholar 

  16. Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: ACL, pp. 311–318 (2002)

    Google Scholar 

  17. Guzmán, F., Joty, S., Màrquez, L., Nakov, P.: Pairwise neural machine translation evaluation. In: ACL, pp. 805–814 (2015)

    Google Scholar 

  18. Graham, Y.: Improving evaluation of machine translation quality estimation. In: ACL, pp. 1804–1813 (2015)

    Google Scholar 

  19. Miceli-Barone, A.V., Attardi, G.: Non-projective dependency-based pre-reordering with recurrent neural network for machine translation. In: ACL, pp. 846–856 (2015)

    Google Scholar 

  20. Zhang, J., Utiyama, M., Sumita, E., Zhao, H.: Learning word reorderings for hierarchical phrase-based statistical machine translation. In: ACL, pp. 542–548 (2015)

    Google Scholar 

  21. Nakagawa, T.: Efficient top-down BTG parsing for machine translation preordering. In: ACL, pp. 208–218 (2015)

    Google Scholar 

  22. Bengio, Y., Ducharme, R., Vincent, P., Jauvin, C.: A neural probabilistic language model. JMLR 3, 1137–1155 (2003)

    MATH  Google Scholar 

  23. Vaswani, A., Zhao, Y., Fossum, V., Chiang, D.: Decoding with large-scale neural language models improves translation. In: EMNLP, pp. 1387–1392 (2013)

    Google Scholar 

  24. Devlin, J., Zbib, R., Huang, Z., Lamar, T., Schwartz, R., Makhoul, J.: Fast and robust neural network joint models for statistical machine translation. In: ACL, pp. 1370–1380 (2014)

    Google Scholar 

  25. Liu, S., Yang, N., Li, M., Zhou, M.: A recursive recurrent neural network for statistical machine translation. In: ACL, pp. 1491–1500 (2014)

    Google Scholar 

  26. Simard, M., Ueffing, N., Isabelle, P., Kuhn, R.: Rule-based translation with statistical phrase-based post-editing. In: SMT, pp. 203–206 (2007)

    Google Scholar 

  27. Dugast, L., Senellart, J., Koehn, P.: Statistical post-editing on SYSTRAN’s rule-based translation system. In: SMT, pp. 220–223 (2007)

    Google Scholar 

  28. Simard, M., Goutte, C., Isabelle, P.: Statistical phrase-based post-editing. In: NAACL, pp. 508–515 (2007)

    Google Scholar 

  29. Isabelle, P., Goutte, C., Simard, M.: Domain adaptation of MT systems through automatic post-editing. In: MT Summit, pp. 255–261 (2007)

    Google Scholar 

  30. Lagarda, A.-L., Alabau, V., Casacuberta, F., Silva, R., Diaz-de-Liano, E.: Statistical post-editing of a rule-based machine translation system. In: ACL, pp. 217–220 (2009)

    Google Scholar 

  31. Béchara, H., Ma, Y., van Genabith, J.: Statistical post-editing for a statistical MT system. In: MT Summit, pp. 308–315 (2011)

    Google Scholar 

  32. Huang, Z., Devlin, J., Matsoukas, S.: BBN’s Systems for the Chinese-English Sub-task of the NTCIR-10 PatentMT Evaluation

    Google Scholar 

  33. Deerwester, S.S., Dumals, T., Furnas, G.W., Landauer, T.K., Harshman, R.: Indexing by Latent semantic analysis. JASIS 41, 391–407 (1990)

    Article  Google Scholar 

  34. Tomas, M., Chen, K., Corrado, G., Dean, J.: Efficient Estimation of Word Representations in Vector Space (2013). arXiv preprint arXiv:1301.3781

  35. Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: NIPS, pp. 3111–3119 (2013)

    Google Scholar 

  36. Huang, E., Socher, R., Manning, C., Ng, A.: Improving word representations via global context and multiple word prototypes. In: ACL, pp. 873–882 (2012)

    Google Scholar 

  37. Le, Q.V., Tomas, M.: Distributed representations of sentences and documents. Eprint Arxiv, pp. 1188–1196 (2014)

    Google Scholar 

  38. Werbos, P.J.: Backpropagation through time: what it does and how to do it, pp. 1550–1560. IEEE (1990)

    Google Scholar 

  39. Eisele, A., Chen, Y.: MultiUN: a multilingual corpus from United Nation documents. In: LREC, pp. 2868–2872 (2010)

    Google Scholar 

  40. Tiedemann, J.: Parallel data, tools and interfaces in OPUS. In: LREC (2012)

    Google Scholar 

  41. Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models. Comput. Linguist. 29(1), 19–51 (2003)

    Article  MATH  Google Scholar 

  42. Koehn, P.F., Och, J., Marcu, D.: Statistical phrase-based translation. In: NAACL, pp. 127–133 (2003)

    Google Scholar 

  43. Och, F.J.: Minimum error rate training in statistical machine translation. In: ACL, pp. 701–711 (2003)

    Google Scholar 

  44. Stolcke, A.: SRILM - an extensible language modeling toolkit. In: ICSLP, pp. 901–904 (2002)

    Google Scholar 

  45. Soricut, R., Marcu, D.: Sentence level discourse parsing using syntactic and lexical information. In: ACL, pp. 149–156 (2003)

    Google Scholar 

  46. Zhang, Z., Zhao, H., Qin, L.: Probabilistic graph-based dependency parsing with convolutional neural network. In: ACL, pp. 1382–1392 (2016)

    Google Scholar 

  47. Cai, D., Zhao, H.: Neural word segmentation learning for Chinese. In: ACL, pp. 409–420 (2016)

    Google Scholar 

  48. Tseng, H., Chang, P., Andrew, G.: A conditional random field word segmenter. In: SIGHAN, Daniel Jurafsky and Christopher Manning (2005)

    Google Scholar 

  49. Chang, P.-C., Galley, M., Manning, C.: Optimizing Chinese word segmentation for machine translation performance. In: WMT, pp. 224–232 (2008)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China

    Chenxi Pang, Hai Zhao & Zhongyi Li

  2. Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China

    Chenxi Pang, Hai Zhao & Zhongyi Li

Authors
  1. Chenxi Pang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hai Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhongyi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hai Zhao .

Editor information

Editors and Affiliations

  1. Tsinghua University , Beijing, China

    Maosong Sun

  2. Fudan University , Shanghai, China

    Xuanjing Huang

  3. Dalian University of Technology , Dalian, China

    Hongfei Lin

  4. Tsinghua University , Beijing, China

    Zhiyuan Liu

  5. Tsinghua University , Beijing, China

    Yang Liu

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing AG

About this paper

Cite this paper

Pang, C., Zhao, H., Li, Z. (2016). I Can Guess What You Mean: A Monolingual Query Enhancement for Machine Translation. In: Sun, M., Huang, X., Lin, H., Liu, Z., Liu, Y. (eds) Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. NLP-NABD CCL 2016 2016. Lecture Notes in Computer Science(), vol 10035. Springer, Cham. https://doi.org/10.1007/978-3-319-47674-2_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-47674-2_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-47673-5

  • Online ISBN: 978-3-319-47674-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation