Abstract
For different language pairs, word-level neural machine translation (NMT) models with a fixed-size vocabulary suffer from the same problem of representing out-of-vocabulary (OOV) words. The common practice usually replaces all these rare or unknown words with a \(\langle \)UNK\(\rangle \) token, which limits the translation performance to some extent. Most of recent work handled such a problem by splitting words into characters or other specially extracted subword units to enable open-vocabulary translation. Byte pair encoding (BPE) is one of the successful attempts that has been shown extremely competitive by providing effective subword segmentation for NMT systems. In this paper, we extend the BPE style segmentation to a general unsupervised framework with three statistical measures: frequency (FRQ), accessor variety (AV) and description length gain (DLG). We test our approach on two translation tasks: German to English and Chinese to English. The experimental results show that AV and DLG enhanced systems outperform the FRQ baseline in the frequency weighted schemes at different significant levels.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
The source code has been released at https://github.com/Lindsay125/gbpe.
- 2.
Though DLG is already frequency weighted as its definition, the proposed extra frequency weight is empirically verified effective from our preliminary experiments.
- 3.
- 4.
“++” indicates that the corresponding BLEU is significantly better than the best score of FRQ\('\)-BPE at the significant level p < 0.01, “+”: p < 0.05.
References
Ataman, D., Federico, M.: Compositional representation of morphologically-rich input for neural machine translation. arXiv preprint arXiv:1805.02036 (2018)
Ataman, D., Negri, M., Turchi, M., Federico, M.: Linguistically motivated vocabulary reduction for neural machine translation from Turkish to English. Prague Bull. Math. Linguist. 108(1), 331–342 (2017)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of 3rd International Conference on Learning Representations (2015)
Bojar, O., et al.: Findings of the 2017 conference on machine translation. In: Proceedings of the 2nd Conference on Machine Translation, vol. 2: Shared Task Papers, pp. 169–214 (2017)
Botha, J., Blunsom, P.: Compositional morphology for word representations and language modelling. In: International Conference on Machine Learning, pp. 1899–1907 (2014)
Cai, D., Zhao, H.: Neural word segmentation learning for Chinese. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 409–420 (2016)
Cai, D., Zhao, H., Zhang, Z., Xin, Y., Wu, Y., Huang, F.: Fast and accurate neural word segmentation for Chinese. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp. 608–615 (2017)
Cettolo, M., Niehues, J., Stüker, S., Bentivogli, L., Federico, M.: Report on the 11th IWSLT evaluation campaign. In: The 11th International Workshop on Spoken Language Translation, Lake Tahoe, USA (2014)
Chung, J., Cho, K., Bengio, Y.: A character-level decoder without explicit segmentation for neural machine translation. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), Berlin, Germany, pp. 1693–1703 (2016)
Collins, M., Koehn, P., Kučerová, I.: Clause restructuring for statistical machine translation. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pp. 531–540 (2005)
Costa-jussà, M.R., Fonollosa, J.A.R.: Character-based neural machine translation. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (vol. 2: Short Papers), Berlin, Germany, pp. 357–361 (2016)
Feng, H., Chen, K., Deng, X., Zheng, W.: Accessor variety criteria for Chinese word extraction. Comput. Linguist. 30(1), 75–93 (2004)
Gage, P.: A new algorithm for data compression. C Users J. 12(2), 23–38 (1994)
Kalchbrenner, N., Blunsom, P.: Recurrent continuous translation models. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Washington, USA, pp. 1700–1709 (2013)
Kit, C.: A goodness measure for phrase learning via compression with the MDL principle. In: Proceedings of the ESSLLI Student Session, pp. 175–187 (1998)
Kit, C., Wilks, Y.: Unsupervised learning of word boundary with description length gain. In: Proceedings of the 3rd Conference on Computational Natural Language Learning, pp. 1–6 (1999)
Lee, J., Cho, K., Hofmann, T.: Fully character-level neural machine translation without explicit segmentation. Trans. Assoc. Comput. Linguist. 5, 365–378 (2017)
Ling, W., Trancoso, I., Dyer, C., Black, A.W.: Character-based neural machine translation. CoRR abs/1511.04586 (2015)
Luong, M.T., Manning, C.D.: Achieving open vocabulary neural machine translation with hybrid word-character models. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), Berlin, Germany, pp. 1054–1063 (2016)
Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal, pp. 1412–1421 (2015)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318 (2002)
Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany, pp. 1715–1725 (2016)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems 27, pp. 3104–3112. Curran Associates, Inc. (2014)
Wu, Y., et al.: Google’s neural machine translation system: bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)
Zhao, H., Kit, C.: An empirical comparison of goodness measures for unsupervised Chinese word segmentation with a unified framework. In: Proceedings of the 3rd International Joint Conference on Natural Language Processing, pp. 9–16 (2008)
Zhao, H., Utiyama, M., Sumita, E., Lu, B.-L.: An empirical study on word segmentation for Chinese machine translation. In: Gelbukh, A. (ed.) CICLing 2013. LNCS, vol. 7817, pp. 248–263. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-37256-8_21
Acknowledgments
This paper was partially supported by National Key Research and Development Program of China (No. 2017YFB0304100), National Natural Science Foundation of China (No. 61672343 and No. 61733011), Key Project of National Society Science Foundation of China (No. 15-ZDA041), The Art and Science Interdisciplinary Funds of Shanghai Jiao Tong University (No. 14JCRZ04).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, Y., Zhao, H. (2018). Finding Better Subword Segmentation for Neural Machine Translation. In: Sun, M., Liu, T., Wang, X., Liu, Z., Liu, Y. (eds) Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. CCL NLP-NABD 2018 2018. Lecture Notes in Computer Science(), vol 11221. Springer, Cham. https://doi.org/10.1007/978-3-030-01716-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-01716-3_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01715-6
Online ISBN: 978-3-030-01716-3
eBook Packages: Computer ScienceComputer Science (R0)