Advertisement

Malay-Corpus-Enhanced Indonesian-Chinese Neural Machine Translation

  • Wuying Liu
  • Lin WangEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 986)

Abstract

Due to the lack of structured language resources, low-resource language machine translation often faces difficulties in cross-language semantic paraphrasing. In order to solve the problem of low-resource machine translation from Indonesian to Chinese, a cognate-parallel-corpus-based expanding method of language resources is proposed, and an improved neural machine translation model is trained by the Malay-corpus-enhanced corpus. The improved model can achieve a comparable result as that of Google in the experiment of Indonesian-Chinese machine translation. The experimental results also show that the morphological similarity and semantic equivalence between the languages are very effective computational features to improve the performance of neural machine translation for low-resource languages.

Keywords

Corpus enhancement Neural machine translation Morphological overlap ratio Corpus transfer ratio Low-resource language 

Notes

Acknowledgements

The research is supported by the Key Project of State Language Commission of China (No. ZDI135-26), the Natural Science Foundation of Guangdong Province (No. 2018A030313672), the Featured Innovation Project of Guangdong Province (No. 2015KTSCX035), the Bidding Project of Guangdong Provincial Key Laboratory of Philosophy and Social Sciences (No. LEC2017WTKT002), and the Key Project of Guangzhou Key Research Base of Humanities and Social Sciences: Guangzhou Center for Innovative Communication in International Cities (No. 2017-IC-02).

References

  1. 1.
    Liu, Y.: Recent advances in neural machine translation. J. Comput. Res. Dev. 54(6), 1144–1149 (2017)Google Scholar
  2. 2.
    Liu, W., Wang, L., Zhang, X.: Fast-syntax-matching-based Japanese-Chinese limited machine translation. In: Gelbukh, A. (ed.) CICLing 2016. LNCS, vol. 9624, pp. 63–73. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-75487-1_6CrossRefGoogle Scholar
  3. 3.
    King, B.P.: Practical Natural Language Processing for Low-Resource Languages. Doctoral dissertation, University of Michigan (2015)Google Scholar
  4. 4.
    Liu, W.: supervised ensemble learning for vietnamese tokenization. Int. J. Uncertainty, Fuzziness Knowl.-Based Syst. 25(2), 285–299 (2017)CrossRefGoogle Scholar
  5. 5.
    Cieri, C., Liberman, M.: TIDES language resources: a resource map for translingual information access. In: Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC), pp. 1334–1339. ELRA (2002)Google Scholar
  6. 6.
    Olive, J., Christianson, C., McCary, J.: Handbook of Natural Language Processing and Machine Translation: DARPA Global Autonomous Language Exploitation. Springer, New york (2011). ISBN 9781441977120CrossRefGoogle Scholar
  7. 7.
    Nakov, P., Ng, H.T.: Improving statistical machine translation for a resource-poor language using related resource-rich languages. J. Artif. Intell. Res. 44, 179–222 (2012)CrossRefGoogle Scholar
  8. 8.
    Koehn, P.: Statistical Machine Translation. Cambridge University Press, Cambridge (2009). ISBN 9780521874151CrossRefGoogle Scholar
  9. 9.
    Bies, A., et al.: A comparison of event representations in DEFT. In: Coreference, and Representation Proceedings of the 4th Workshop on Events: Definition, Detection, pp. 27–36. ACL (2016)Google Scholar
  10. 10.
    Cieri, C., Maxwell, M., Strassel, S., Tracey, J.: Selection criteria for low resource language programs. In: Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC), pp. 4543–4549. ELRA (2016)Google Scholar
  11. 11.
    Knill, K.M., Gales, M.J.F., Ragni, A., Rath, S.P.: Language independent and unsupervised acoustic models for speech recognition and keyword spotting. In: Proceedings the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 16–20. ISCA (2014)Google Scholar
  12. 12.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)CrossRefGoogle Scholar
  13. 13.
    Hirschberg, J., Manning, C.D.: Advances in natural language processing. Science 349(6245), 261–266 (2015)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Vaswani, A., et al.: Attention Is All You Need. arXiv:1706.03762v5 (2017)
  15. 15.
    Artetxe, M., Labaka, G., Agirre, E., Cho, K.: Unsupervised Neural Machine Translation. arXiv:1710.11041v1 (2017)
  16. 16.
    Wu, Y.: Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. arXiv:1609.08144v2 (2016)
  17. 17.
    Manning, C.D.: Last words: computational linguistics and deep learning. Comput. Linguist. 41(4), 701–707 (2015)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Zhang, J., Zong, C.: Deep neural networks in machine translation: an overview. IEEE Intell. Syst. 30(5), 16–25 (2015)CrossRefGoogle Scholar
  19. 19.
    Liu, W., Lin, L.: Probabilistic ensemble learning for vietnamese word segmentation. In: Proceedings of the 37th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 931–934. ACM (2014)Google Scholar
  20. 20.
    Koehn, P., Hoang, H., Birch, A., et al.: Moses: open source toolkit for statistical machine translation. In: Annual Meeting of the Association for Computational Linguistics (ACL), Demonstration Session, Prague, Czech Republic, June 2007Google Scholar
  21. 21.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 28th Annual Conference on Neural Information Processing Systems (NIPS), pp. 3104–3112. Curran Associates (2014)Google Scholar
  22. 22.
    Neubig, G.: Neural Machine Translation and Sequence-to-sequence Models: A Tutorial. arXiv:1703.01619v1 (2017)

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Laboratory of Language Engineering and ComputingGuangdong University of Foreign StudiesGuangzhouChina
  2. 2.School of Information Science and TechnologyJiujiang UniversityJiujiangChina
  3. 3.Xianda College of Economics and HumanitiesShanghai International Studies UniversityShanghaiChina

Personalised recommendations