Abstract
In both SMT (statistical machine translation) and NMT (neural machine translation), training data often varies in source, theme and genre. It is less likely that the training data and texts in practical translation fall into a same domain, leading to a sub-optimal performance. Domain adaptation is to address such problems. Existing domain adaptive approach in machine translation employs topic model to obtain topic information. However, thus domain labels can be very much limited to in-domain and out-of-domain, when dividing topics into two types, without any more specific labels. We propose a novel domain adaptive approach to annotate Chinese sentences with CLCN (Chinese Library Classification Number) as the domain labels. We design a deep fusion model of neural network to combine two annotating models, including one applying a domain knowledge base built on thesis keywords and Chinese Scientific and Technical Vocabulary System, and the other applying deep learning method based on a CNN. Then, we have the fused domain annotator to filter the training data of NMT according to the test data. After running two predefined domain test sets on a NMT system trained by only partial of the original training data, we achieve an average 1.3 BLEU score improvement (5.4% relative), which demonstrates the feasibility and validity of proposed approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Luong, M.T, Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate: arXiv preprint arXiv:1409.0473 (2014)
Shunian, C.: The first electronic edition of Chinese library classification. Lib. Inf. Serv. 3, 55–60 (2002)
ISTIC.: Chinese Scientific & Technical Vocabulary System. Science and Technology Literature Press, Beijing (2014)
Eck, M., Vogel, S., Waibel, A.: Low cost portability for statistical machine translation based on n-gram coverage. In: Proceedings of Mtsummit X (2005)
Zhao, B., Eck, M., Vogel, S.: Language model adaptation for statistical machine translation with structured query models. In: Proceedings of 20th International Conference on Computational Linguistics, p. 411. Association for Computational Linguistics, The University of Geneva, Switzerland (2004)
Lü, Y., Huang, J., Liu, Q.: Improving statistical machine translation performance by training data selection and optimization. In: EMNLP-CoNLL 2007, Proceedings of 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 28–30 June 2007, Prague, Czech Republic, pp. 343–350 (2007)
Koehn, P., Schroeder, J.: Experiments in domain adaptation for statistical machine translation. In: Proceedings of 2nd, Workshop on Statistical Machine Translation, pp. 224–227. Association for Computational Linguistics, Prague (2007)
Finch, A., Sumita, E.: Dynamic model interpolation for statistical machine translation. In: Proceedings of 3rd Workshop on Statistical Machine Translation, pp. 208–215. Association for Computational Linguistics, Columbus (2008)
Ueffing, N., Haffari, G., Sarkar, A.: Semi-supervised model adaptation for statistical machine translation. Mach. Transl. 21, 71–94 (2007)
Wu, H., Wang, H., Zong, C.: Domain adaptation for statistical machine translation with domain dictionary and monolingual corpora. In: Proceedings of 22nd International Conference on Computational Linguistics (Coling 2008), pp. 993–1000. COLING 2008 Organizing Committee, Manchester (2008)
Luong, M.-T., Manning, C. D.: Stanford neural machine translation systems for spoken language domains. In: International Workshop on Spoken Language Translation (2015)
Zhao, B., Xing, E.P.: BiTAM: bilingual topic admixture models for word alignment. In: Proceedings of COLING/ACL 2006 Main Conference Poster Sessions, pp. 969–976. Association for Computational Linguistics, Sydney (2006)
Zhao, B., Xing, E.P.: HM-BiTAM: bilingual topic exploration, word alignment, and translation. In: Advances in Neural Information Processing Systems, pp. 1689–1696. Vancouver, British Columbia (2008)
Xiao, X., Xiong, D., Zhang, M., et al.: A topic similarity model for hierarchical phrase-based translation. In: Proceedings of 50th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 750–758. Association for Computational Linguistics, Jeju (2012)
Zhang, J., Li, L., Andy, W., Liu, Q.: Topic-informed neural machine translation. In: Proceedings of 26th International Conference on Computational Linguistics: Technical Papers, pp. 1807–1817 (2016)
Chu, C., Dabre, R., Kurohashi, S.: An empirical comparison of domain adaptation methods for neural machine translation. In: Meeting of Association for Computational Linguistics (ACL 2017), pp. 385–391 (2017)
Freitag, M., Al-Onaizan, Y.: Fast domain adaptation for neural machine translation. arXiv preprint arXiv:1612.06897 (2016)
Ding, L., Li, Y., He, Y., Wang, X., Zhang, Y., Yao, C.: Experimental study on training data selection of SMT based on Chinese thesaurus. J. China Soc. Sci. Tech. Inf. J. 35(8), 875–884 (2016)
Ding, L., Li, Y., He, Y., Liu, J.: Research on Japanese-Chinese S&T terminology translation based-on two-dimensional domain lexicalized domain knowledge. In: CWMT 2016, Urumchi, China, vol. 8, pp. 25–26 (2016)
He, Y., Ding, L., Li, Y.: Research on domain adaptation for SMT based on specific domain knowledge. In: Yang, M., Liu, S. (eds.) CWMT 2016. CCIS, vol. 668, pp. 43–60. Springer, Singapore (2016). https://doi.org/10.1007/978-981-10-3635-4_5
Ding, L., Yao, C., He, Y., et al.: Application of deep learning in statistical machine translation domain adaptation. J. Technol. Intell. Eng. 3(3), 64–76 (2016)
Sun, M., Wang, H., Li, X., et al.: The guideline of constructing a wordlist of contemporary Chinese for information processing. J. Appl. Linguist. J. 2001(4), 84–89 (2001)
Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188 (2014)
Acknowledgments
This research work was partially supported by National Natural Science of China (61303152, 71503240, 71403257), and ISTIC Research Foundation Projects (ZD2017-4).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ding, L., He, Y., Zhou, L., Liu, Q. (2017). Combining Domain Knowledge and Deep Learning Makes NMT More Adaptive. In: Wong, D., Xiong, D. (eds) Machine Translation. CWMT 2017. Communications in Computer and Information Science, vol 787. Springer, Singapore. https://doi.org/10.1007/978-981-10-7134-8_9
Download citation
DOI: https://doi.org/10.1007/978-981-10-7134-8_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-7133-1
Online ISBN: 978-981-10-7134-8
eBook Packages: Computer ScienceComputer Science (R0)