Abstract
Neural Machine Translation (NMT), increased the accuracy of machine translation and recently become more popular in machine translation research community. An attention mechanism has been added with NMT and the result of MT is improving, respectively. Using different attention mechanism in encoder-decoder, along with NMT models are achieving good results considering mentionable improvements in source sentences during the translation. Translating from English to another language is a widely used machine translation problem. For this regard, English-Bengali translation is a researchable area in Bengali machine translation. Bengali is one of the usable languages in the world. Therefore, conversion of Bengali to other language is very essential for people. The translator is a way to understand the meaning of different language. But sometimes the translator does not provide the accurate Bengali translation for the corresponding English text. So, generating the correct English to Bengali translation requires more research. In this research, we build an attention-based NMT model for English to Bengali machine translation instead of the normal NMT model and that achieves 22.3 BELU for model evaluation. Also, we build a seq2seq model without attention for checking the machine performance on translation. That achieves 15.3 BELU for the applied dataset. The analysis shows that the attention-based seq2seq model performs better than seq2seq learning for English to Bengali translation.
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
References
O. Kuchaiev, B. Ginsburg, I. Gitman, V. Lavrukhin, J. Li, H. Nguyen, C. Case, P. Micikevicius, Mixed-precision training for NLP and speech recognition with open seq2seq (2018)
T. Poibeau, Machine Translation. (MIT Press, 2017)
A. Waibel, A. N. Jain, A. E. McNair, H. Saito, A. Hauptmann, J. Tebelskis, Janus: a speech-to-speech translation system using connectionist and symbolic processing strategies, in Proceedings of the ICASSP (1991), pp. 793–796
M.A. Hasan, F. Alam, S.A. Chowdhury, N. Khan, Neural machine translation for the Bangla-English language pair, in 2019 22nd International Conference on Computer and Information Technology (ICCIT). (IEEE, 2019), pp. 1–6
K. Cho, B. Van Merriënboer, D. Bahdanau, Y. Bengio, On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)
I. Sutskever, O. Vinyals, Q.V. Le, Sequence to sequence learning with neural networks, in Advances in Neural Information Processing Systems (2014), pp. 3104–3112
N. Kalchbrenner, P. Blunsom, Recurrent continuous translation models, in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (2013), pp. 1700–1709
D. Bahdanau, K. Cho, Y. Bengio, Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
J. Su, X. Zhang, Q. Lin et al., Exploiting reverse target-side contexts for neural machine translation via asynchronous bidirectional decoding. Artif. Intell. 277 (2019)
K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, Y. Bengio, Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
M.T. Luong, H. Pham, C.D. Manning, Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)
Z. Tu et al., Modeling coverage for neural machine translation. arXiv reprint arXiv:1601.04811 (2016)
M.A. Hasan, F. Alam, S.R.H. Noori, A collaborative platform to collect data for developing machine translation systems, in Proceedings of International Joint Conference on Computational Intelligence. Algorithms for Intelligent Systems edited by M. Uddin, J. Bansal. (Springer, Singapore, 2020)
Acknowledgements
We gratefully acknowledge support from DIU NLP and Machine Learning Research LAB for providing GPUs support. We thank, Dept. of CSE, Daffodil International University for providing necessary supports. And also thanks to the anonymous reviewers for their valuable comments and feedback.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Abujar, S., Masum, A.K.M., Bhattacharya, A., Dutta, S., Hossain, S.A. (2021). English to Bengali Neural Machine Translation Using Global Attention Mechanism. In: Tavares, J.M.R.S., Chakrabarti, S., Bhattacharya, A., Ghatak, S. (eds) Emerging Technologies in Data Mining and Information Security. Lecture Notes in Networks and Systems, vol 164. Springer, Singapore. https://doi.org/10.1007/978-981-15-9774-9_35
Download citation
DOI: https://doi.org/10.1007/978-981-15-9774-9_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-9773-2
Online ISBN: 978-981-15-9774-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)