Abstract
Machine translation is one of the challenging Artificial Intelligence areas due to the complexity of the languages. Models that use Recurrent Neural Networks (RNN) such as Sequence-to-Sequence model have become popular on many Natural Language Processing (NLP) problems including machine translation. However, these models underperform on long sentences due to fixed length vector design. In this paper, we deployed a RNN based Sequence-to-Sequence model and Long Short-Term Memory (LSTM) with attention trained for Machine Translation (MT). We evaluated our model on a Turkish to English dataset. In addition, we have created a dataset with words from Ottoman literature which we plan to use in our future studies. We believe that this dataset will be a very valuable data source as not many NLP studies have been done with Ottoman literature. The effect of hyperparameters is also examined.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ataman, D., Negri, M., Turchi, M., Federico, M.: Linguistically motivated vocabulary reduction for neural machine translation from Turkish to English. In: The Prague Bulletin of Mathematical Linguistics
Berger, A., Brown, P.F., Della Pietra, S.A., Della Pietra, V.J., Gillett, J.R., Lafferty, J., Mercer, R.L., Printz, H., Ures, L.: The candide system for machine translation. In: Human Language Technology: Proceedings of a Workshop held at Plainsboro, New Jersey, March 8-11, 1994 (1994)
Cambria, E., White, B.: Jumping nlp curves: A review of natural language processing research [review article]. IEEE Comput. Intell. Mag. 9(2), 48–57 (2014)
Deselaers, T., Hasan, S., Bender, O., Ney, H.: A deep learning approach to machine transliteration. In: Proceedings of the Fourth Workshop on Statistical Machine Translation, pp. 233–241 (2009)
He, X., Haffari, G., Norouzi, M.: Sequence to sequence mixture model for diverse machine translation. arXiv preprint arXiv:1810.07391 (2018)
Johnson, M., Schuster, M., Le, Q.V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F., Wattenberg, M., Corrado, G., Hughes, M., Dean, J.: Google’s multilingual neural machine translation system: Enabling zero-shot translation. In: Transactions of the Association for Computational Linguistics, pp. 339–351 (2017)
Klein, G., Kim, Y., Deng, Y., Senellart, J., Rush, A.M.: Opennmt: Open-source toolkit for neural machine translation. arXiv preprint arXiv:1701.02810 (2017)
Koehn, P., Hoang, H.: Factored translation models. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 868–876 (2007)
Otter, D.W., Medina, J.R., Kalita, J.K.: A survey of the usages of deep learning for natural language processing. In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1–21 (2020)
Pytorch: Nlp from scratch (2017), https://pytorch.org/tutorials/, [Online; Accessed 29 Aug 2020]
Weiss, R.J., Chorowski, J., Jaitly, N., Wu, Y., Chen, Z.: Sequence-to-sequence models can directly translate foreign speech. arXiv preprint arXiv:1703.08581 (2017)
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 Switzerland AG
About this paper
Cite this paper
Balki, F., Demirhan, H., Sarp, S. (2021). Neural Machine Translation for Turkish to English Using Deep Learning. In: Biele, C., Kacprzyk, J., Owsiński, J.W., Romanowski, A., Sikorski, M. (eds) Digital Interaction and Machine Intelligence. MIDI 2020. Advances in Intelligent Systems and Computing, vol 1376. Springer, Cham. https://doi.org/10.1007/978-3-030-74728-2_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-74728-2_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-74727-5
Online ISBN: 978-3-030-74728-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)