Abstract
Recently, neural machine translation (NMT) has become highly successful achieving state-of-the-art results on many resource-rich language pairs. However, it fails when there is a lack of sufficiently large amount of parallel corpora for a domain and/or language pair. In this paper, we propose an effective method for NMT under a low-resource scenario. The model operates by augmenting the original training data with the examples extracted from the parse trees of the target-side sentences. It provides important evidences to the model as these phrases are relatively smaller and linguistically correct. Our experiment on the benchmark WMT14 dataset shows an improvement of 3.28 BLEU and 3.41 METEOR score for Hindi to English translation. Evaluation on the same language pair with relatively much smaller datasets of judicial and health domains also show the similar trends with significant performance improvement in terms of BLEU (15.63 for judicial and 15.97 for health) and METEOR (14.30 for judicial and 15.93 for health).
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
Notes
- 1.
Linguistically more accurate as the lengths are short.
- 2.
- 3.
- 4.
It is based on BLEU score with patience value = 10.
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: International Conference on Learning Representation (ICLR) (2015)
Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pp. 65–72. Association for Computational Linguistics (2005). http://www.aclweb.org/anthology/W05-0909
Bojar, O., et al.: Findings of the 2014 workshop on statistical machine translation. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 12–58 (2014)
Bojar, O., et al.: Findings of the 2016 conference on machine translation. In: ACL 2016 First Conference on Machine Translation (WMT16), pp. 131–198. The Association for Computational Linguistics (2016)
Bojar, O., et al.: Hindencorp-Hindi-English and Hindi-only corpus for machine translation. In: LREC, pp. 3550–3555 (2014)
Crego, J., et al.: Systran’s pure neural machine translation systems. arXiv preprint arXiv:1610.05540 (2016)
Currey, A., Barone, A.V.M., Heafield, K.: Copied monolingual data improves low-resource neural machine translation. In: Proceedings of the Second Conference on Machine Translation, pp. 148–156 (2017)
Federico, M., Bertoldi, N., Cettolo, M.: IRSTLM: an open source toolkit for handling large scale language models. In: Ninth Annual Conference of the International Speech Communication Association (2008)
Gulcehre, C., et al.: On using monolingual corpora in neural machine translation. arXiv preprint arXiv:1503.03535 (2015)
Junczys-Dowmunt, M., Dwojak, T., Hoang, H.: Is neural machine translation ready for deployment? A case study on 30 translation directions. In: In Proceedings of the International Workshop on Spoken Language Translation (IWSLT) (2016)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representation (ICLR) (2015)
Kneser, R., Ney, H.: Improved backing-off for m-gram language modeling. In: Acoustics, Speech, and Signal Processing, 1995. ICASSP-95, 1995 International Conference on, vol. 1, pp. 181–184. IEEE (1995)
Koehn, P., et al.: Moses: open source toolkit for statistical machine translation. In: Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions, pp. 177–180. Association for Computational Linguistics (2007)
Koehn, P., Knowles, R.: Six challenges for neural machine translation. In: Proceedings of the First Workshop on Neural Machine Translation, pp. 28–39. Association for Computational Linguistics, Vancouver, August 2017. http://www.aclweb.org/anthology/W17-3204
Koehn, P., Och, F.J., Marcu, D.: Statistical phrase-based translation. In: Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, vol. 1, pp. 48–54. Association for Computational Linguistics (2003)
Och, F.J.: Minimum error rate training in statistical machine translation. In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, vol. 1, pp. 160–167. Association for Computational Linguistics (2003)
Och, F.J., Ney, H.: A systematic comparison of various statistical alignment models. Comput. Linguist. 29(1), 19–51 (2003)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting on association for computational linguistics, pp. 311–318. Philadelphia, Pennsylvania (2002)
Sennrich, R., et al.: Nematus: a toolkit for neural machine translation. arXiv preprint arXiv:1703.04357 (2017)
Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. arXiv preprint arXiv:1511.06709 (2015)
Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, 7–12 August 2016, Berlin, Germany (2016)
Wu, Y., et al.: Google’s neural machine translation system: bridging the gap between human and machine translation. CoRR abs/1609.08144 (2016). http://arxiv.org/abs/1609.08144
Zhang, J., Zong, C.: Exploiting source-side monolingual data in neural machine translation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1535–1545 (2016)
Acknowledgement
We gratefully acknowledge TDIL, MeitY who supported this research work under development of the project “Hindi to English machine translation for judicial domain”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Nature Switzerland AG
About this paper
Cite this paper
Gupta, K.K., Sen, S., Ekbal, A., Bhattacharyya, P. (2023). Improving Low-Resource NMT with Parser Generated Syntactic Phrases. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2019. Lecture Notes in Computer Science, vol 13451. Springer, Cham. https://doi.org/10.1007/978-3-031-24337-0_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-24337-0_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-24336-3
Online ISBN: 978-3-031-24337-0
eBook Packages: Computer ScienceComputer Science (R0)