Abstract
Recently, research on machine translation has been active, and research on the Transformer, which is a translation component of the open source library Tensor2Tensor, is also active. In July 2020, a development research institute called Open AI announced GPT − 3 (Generative Pretrained Transformer), a sentence generation language model, uses 175 billion parameters and is evaluated as an AI tool that generates sentences as if they were written by humans. Using this Transformer, we are also constructing a Braille translation system using a neural network. To translate Japanese into Braille, we devised a three-step process. The first is the step of converting a kana-kanji mixed sentence into a space-inserted sentence, the second is the step of converting the space-inserted sentence into a phonetic kana sentence, and the third is the step of converting the phonetic kana sentence into Braille. Earlier at ICMSEM 2019, we have presented the third step. This time, we have developed the first and second steps. That is, the input data are the kana − kanji mixed sentence of step 1, and the output is the phonetic kana sentence of step 2. The whole picture of this system and the steps developed this time is described.
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
Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th \(\{\)USENIX\(\}\) Symposium on Operating Systems Design and Implementation (\(\{\)OSDI\(\}\) 2016), pp. 265–283 (2016)
Committee, J.B.: Revised Japan Braille Notation. Japan Braille Committee (2018)
Developer, N.: CUDA Toolkit (2021). https://developer.nvidia.com/cuda-toolkit
Gillioz, A., Casas, J.: Overview of the transformer-based models for NLP tasks. In: 2020 15th Conference on Computer Science and Information Systems (FedCSIS), pp. 179–183. IEEE (2020)
Goldberg, A., Schreier, E., Leventhal, J., De Witt, J.: An evaluation of braille translation programs. J. Visual Impairment Blindness 81(10), 487–492 (1987)
Goto, I., Tanaka, H.: Detecting untranslated content for neural machine translation. In: Proceedings of the First Workshop on Neural Machine Translation, pp. 47–55 (2017)
Kokura, H.: Japanese Vocabulary and Notation Japanese Vocabulary and Notation. Corpus-Based Learning of Japanese. Kadokawa Publishing Co., Ltd. (2020)
Mi, H., Sankaran, B.: Coverage embedding models for neural machine translation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, vol. 1, pp. 955–960 (2016)
Morohashi Tea: Great Kanji dictionary Digital Edition. TAISHUKAN Publishing Co. Ltd. (2019). (in Japanese)
Pouyanfar, S., Sadiq, S., Yan, Y.: A survey on deep learning: algorithms, techniques, and applications. ACM Comput. Surv. (CSUR) 51(5), 1–36 (2018)
Rogers, A., Kovaleva, O., Rumshisky, A.: A primer in bertology: what we know about how bert works written by anna rogers. Trans. Assoc. Comput. Linguist. 8, 842–866 (2021)
Shimomura, Y., Kawabe, H.: Braille translation system in japan-past and now. In: Proceedings of the Asia Pacific Industrial, Engineering and Management Systems, vol. 6, pp. 24–29 (2017)
Shimomura, Y., Kawabe, H.: Development of a system that beginner volunteers can translate Japanese into Braille. In: Proceedings of the Asia Pacific Industrial, Engineering and Management Systems (2018)
Shimomura, Y., Kawabe, H.: The translation system from Japanese into braille by using MeCab. In: Proceedings of the International Conference on Management Science and Engineering Management, vol. 1, pp. 1125–1134 (2018)
Tetko, I., Karpov, P.: State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis. Nat. Commun. 11(1), 1–11 (2020)
Tu, Z., Liu, Y.: Neural machine translation with reconstruction. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31, pp. 3097–3103 (2017)
Tu, Z., Liu, Y.: Modeling coverage for neural machine translation. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 76–85 (2016)
Vaswani, A., Shazeer, N.: Attention is all you need [transformer]. In: The 31st Conference on Neural Information Processing Systems (NIPS 2017), p. 30 (2017)
For Providing Facilities for the Visually Impaired NA: Braille transcription guide Fourth Edition. National Association for Providing Facilities for the Visually Impaired (2017)
Yuta Tuboi ea: Natural language processing by deep learning. Kodansya (2017). (in Japanese)
Acknowledgements
This work was supported by JSPS KAKENHI Grant number 17k01097. I appreciate it deeply.
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
Kawabe, H., Shimomura, Y., Seto, S. (2021). Braille Translation System Using Neural Machine Translation Technology II – Code Conversion of Kana-Kanji Mixed Sentences. In: Xu, J., García Márquez, F.P., Ali Hassan, M.H., Duca, G., Hajiyev, A., Altiparmak, F. (eds) Proceedings of the Fifteenth International Conference on Management Science and Engineering Management. ICMSEM 2021. Lecture Notes on Data Engineering and Communications Technologies, vol 78. Springer, Cham. https://doi.org/10.1007/978-3-030-79203-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-79203-9_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-79202-2
Online ISBN: 978-3-030-79203-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)