Abstract
Machine translation has achieved impressive performance with the advances in deep learning and rely on large scale parallel corpora. There have been a large number of attempts to extend these successes to low-resource language, yet requiring large parallel sentences. In this study, we build the Mongolian-Chinese neural machine translation model based on unsupervised methods. Cross-lingual word embedding training plays a crucial role in unsupervised machine translation which generative adversarial networks (GANs) training methods only perform well between two closely-related languages, yet the self-learning method can learn high-quality bilingual embedding mappings without any parallel corpora in low-source language. In this work, apply the self-learning method is better than using GANs to improve the BLEU score of 1.0. On this basis, we analyze the Mongolian word lexical features and use stem-affixes segmentation in Mongolian to replace the Bytes-Pair-Encoding (BPE) operation, so that the cross-lingual word embedding training is more accurate, and obtain higher quality bilingual words embedding to enhance translation performance. We reporting BLEU score of 15.2 on the CWMT2017 Mongolian-Chinese dataset, without using any parallel corpora during training.
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
References
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Neural Information Processing Systems (NIPS), pp. 3104–3112 (2014)
Bahdanau, D., Cho, K., Bengio, Y., et al.: Neural machine translation by jointly learning to align and translate. In: International Conference on Learning Representations (ICLR). arXiv preprint arXiv:1409(0473) (2015)
Wu, Y., Schuster, M., Chen, Z., et al.: Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. arXiv: Computation and Language (2016)
Lample, G., Conneau, A., Denoyer, L., et al.: Unsupervised machine translation using monolingual corpora only. In: International Conference on Learning Representations (ICLR). arXiv preprint arXiv:1711(00043) (2018)
Artetxe, M., Labaka, G., Agirre, E., et al.: Unsupervised neural machine translation. In: International Conference on Learning Representations (ICLR). arXiv preprint arXiv:1710(11041) (2018)
Wu, J., Hou, H., Shen, Z., et al.: Adapting attention-based neural network to low-resource Mongolian-Chinese machine translation. In: International Conference on the Computer Processing of Oriental Languages (ICCPOL), pp. 470–480 (2016)
Fan, W., Hou, H., Wang, H., et al.: Machine translation model of Mongolian-Chinese neural network fusing priori information. Chin. J. Inf. Sci. 32(06), 36–43 (2018)
Jinting, L., Hongxu, H., Jing, W., et al.: Combining discrete lexicon probabilities with NMT for low-resource Mongolian-Chinese translation. In: Parallel and Distributed Computing: Applications and Technologies (PDCAT), pp. 104–111 (2017)
Wang, H.: Multi-granularity Mongolian Chinese neural network machine translation research. In: Inner Mongolia University, pp. 15–35 (2018)
Artetxe, M., Labaka, G., Agirre, E., et al.: Learning bilingual word embeddings with (almost) no bilingual data. In: Meeting of the Association for Computational Linguistics (MACL), pp. 451–462 (2017)
Lample, G., Conneau, A., Ranzato, M., et al.: Word translation without parallel data. In: International Conference on Learning Representations (ICLR). arXiv preprint arXiv:1710(04087) (2018)
He, D., Xia, Y., Qin, T., et al.: Dual learning for machine translation. In: Neural Information Processing Systems (NICS), pp. 820–828 (2016)
Jiang, W., Wu, J., Wu, R., et al.: Discriminant stem affixation of Mongolian directed graph morphology analyzer. J. Chin. Inf. Process. 25(04), 30–34 (2011)
Gouws, S., Bengio, Y., et al.: BilBOWA: fast bilingual distributed representations without word alignments. In: International Conference on Machine Learning (ICML), pp. 748–756 (2015)
Sennrich, R., Haddow, B., Birch, A., et al.: Improving neural machine translation models with monolingual data. In: Meeting of the Association for Computational Linguistics (MACL), pp. 86–96 (2016)
Lample, G., Ott, M., Conneau, A., et al.: Phrase-based & neural unsupervised machine translation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 5039–5049 (2018)
Yang, Z., Chen, W., Wang, F., et al.: Improving neural machine translation with conditional sequence generative adversarial nets. In: North American chapter of the association for computational linguistics (NAACL), pp. 1346–1355 (2018)
Barone, A.: Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders. In: Meeting of the Association for Computational Linguistics (ACL), pp. 121–126 (2016)
Artetxe, M., Labaka, G., Agirre, E.: A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 789–798 (2018)
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, Z., Hou, H., Guo, Z., Wang, X., Sun, S. (2019). Mongolian-Chinese Unsupervised Neural Machine Translation with Lexical Feature. In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds) Chinese Computational Linguistics. CCL 2019. Lecture Notes in Computer Science(), vol 11856. Springer, Cham. https://doi.org/10.1007/978-3-030-32381-3_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-32381-3_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32380-6
Online ISBN: 978-3-030-32381-3
eBook Packages: Computer ScienceComputer Science (R0)