Abstract
Domain mismatch between training data and test data often degrades translation quality. It is necessary to make domain adaptation for machine translation tasks. In this paper, we propose a novel method to tackle Neural Machine Translation (NMT) domain adaptation issue, where a soft-domain adapter (SDA) is added in the encoder-decoder NMT framework. Our SDA automatically learns domain representations from the training corpus, and dynamically compute domain-aware context for inputs which can guide the decoder to generate domain-aware translations. Our method can softly leverage domain information to translate source sentences, which can not only improve the translation quality on specific domain but also be robust and scalable on different domains. Experiments on Chinese-English and English-French tasks show that our proposed method can significantly improve the translation quality of in-domain test sets, without performance sacrifice of out-of-domain/general-domain data sets.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
In the rest of this paper, the characters in bold refer to vectors.
- 2.
LDC2002E17, LDC2002E18, LDC2003E07, LDC2003E14, LDC2005E83, LDC2005T06, LDC2005T10, LDC2006E17, LDC2006E26, LDC2006E34, LDC2006E85, LDC2006E92, LDC2006T06, LDC2004T08, LDC2005T10.
- 3.
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: ICLR 2015 (2015)
Cettolo, M., Niehues, J., Stüker, S., Bentivogli, L., Cattoni, R., Federico, M.: The IWSLT 2015 evaluation campaign. In: Proceedings of IWSLT, Da Nang, Vietnam (2015)
Cettolo, M., Niehues, J., Stüker, S., Bentivogli, L., Federico, M.: Report on the 11th IWSLT evaluation campaign. In: Proceedings of the International Workshop on Spoken Language Translation, IWSLT 2014, Hanoi, Vietnam (2014)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of ENMLP 2014 (2014)
Chu, C., Dabre, R., Kurohashi, S.: An empirical comparison of simple domain adaptation methods for neural machine translation. arXiv preprint arXiv:1701.03214 (2017)
Freitag, M., Al-Onaizan, Y.: Fast domain adaptation for neural machine translation. arXiv preprint arXiv:1612.06897 (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kobus, C., Crego, J., Senellart, J.: Domain control for neural machine translation. arXiv preprint arXiv:1612.06140
Luong, M.T., Manning, C.D.: Stanford neural machine translation systems for spoken language domains. In: Proceedings of IWSLT 2015 (2015)
Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of EMNLP 2015 (2015)
Luong, T., Sutskever, I., Le, Q., Vinyals, O., Zaremba, W.: Addressing the rare word problem in neural machine translation. In: Proceedings of ACL 2015 (2015)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of ACL 2002 (2002)
Pryzant, R., Britz, D., Le, Q.: Effective domain mixing for neural machine translation. In: Second Conference on Machine Translation (WMT) (2017)
Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)
Servan, C., Crego, J., Senellart, J.: Domain specialization: a post-training domain adaptation for neural machine translation. arXiv preprint arXiv:1612.06141 (2016)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems (2014)
Vaswani, A., et al.: Attention is all you need. Curran Associates, Inc. (2017)
Wang, R., Utiyama, M., Liu, L., Chen, K., Sumita, E.: Instance weighting for neural machine translation domain adaptation. In: Proceedings of EMNLP 2017 (2017)
Wu, Y., et al.: Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, S., Zhang, D., Zhou, M. (2019). Effective Soft-Adaptation for Neural Machine Translation. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11839. Springer, Cham. https://doi.org/10.1007/978-3-030-32236-6_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-32236-6_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32235-9
Online ISBN: 978-3-030-32236-6
eBook Packages: Computer ScienceComputer Science (R0)
