Abstract
We propose a Transformer-based differential translation architecture that targets statutory sentences partially modified by amendments. In translating post-amendment statutory sentences, translation focality—modifying only the amended expressions in the translation and retaining the others—is important to avoid misunderstanding the amendment’s contents. To sharpen the translation’s focality, we introduce a neural network architecture called a Copiable Translation Transformer that can copy expressions in the pre-amendment translated sentence as needed and generate expressions from the post-amendment original sentence. In experiments, we showed that our method outperformed the naive Transformer with a training corpus of partially amended sentences.
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.
JLT has a function for browsing statutes and the translations of different amendment versions.
- 2.
https://elaws.e-gov.go.jp/ The e-Legislative Activity and Work Support System (e-LAWS) provides an open governmental database of the most recent, original national statutes (i.e., written in Japanese).
- 3.
We kept the remaining 132 examples (eight amendment cases) for a development dataset for future use.
- 4.
References
Gu, J., Lu, Z., Li, H., Li, V.O.: Incorporating copying mechanism in sequence-to-sequence learning. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 1631–1640 (2016)
Hirao, T., Isozaki, H., Sudoh, K., Duh, K., Tsukada, H., Nagata, M.: Evaluating translation quality with word order correlations. J. Nat. Lang. Process. 21(3), 421–444 (2014). (In Japanese)
Hoseishitsumu-Kenkyukai: Workbook Hoseishitsumu (newly revised second edition). Gyosei (2018). (In Japanese)
Huang, X., Liu, Y., Luan, H., Xu, J., Sun, M.: Learning to copy for automatic post-editing. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 6122–6132 (2019)
Koehn, P., et al.: Moses: open source toolkit for statistical machine translation. In: Proceedings of the ACL 2007 Demo and Poster Sessions, pp. 177–180 (2007)
Koehn, P., Senellart, J.: Convergence of translation memory and statistical machine translation. In: AMTA Workshop on MT Research and the Translation Industry, pp. 21–31 (2010)
Kozakai, T., Ogawa, Y., Ohno, T., Nakamura, M., Toyama, K.: Shinkyutaishohyo no riyo niyoru horei no eiyaku shusei. In: Proceedings of NLP2017, 4 p. (2017) (In Japanese)
Kudo, T., Richardson, J.: Sentencepiece: a simple and language independent subword tokenizer and detokenizer for neural text processing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations), pp. 66–71 (2018)
Ogawa, Y., Inagaki, S., Toyama, K.: Automatic consolidation of Japanese statutes based on formalization of amendment sentences. In: Satoh, K., Inokuchi, A., Nagao, K., Kawamura, T. (eds.) JSAI 2007. LNCS (LNAI), vol. 4914, pp. 363–376. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-78197-4_34
Papineni, K., Roukos, S., Ward, T., Jing Zhu, W.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318 (2002)
Toyama, K., et al.: Design and development of Japanese law translation system. In: Law via the Internet 2011, 12 p. (2011)
Vaswani, A., et al.: Attention is all you need. In: Proceedings of Advances in Neural Information Processing Systems, vol. 30, pp. 6000–6010 (2017)
Xia, M., Huang, G., Liu, L., Shi, S.: Graph based translation memory for neural machine translation. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, pp. 7297–7304 (2019)
Xu, S., Li, H., Yuan, P., Wu, Y., He, X., Zhou, B.: Self-attention guided copy mechanism for abstractive summarization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 1355–1362 (2020)
Yamakoshi, T., Komamizu, T., Ogawa, Y., Toyama, K.: Differential translation for Japanese partially amended statutory sentences. In: Okazaki, N., Yada, K., Satoh, K., Mineshima, K. (eds.) JSAI-isAI 2020. LNCS (LNAI), vol. 12758, pp. 162–178. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-79942-7_11
Yamakoshi, T., Komamizu, T., Ogawa, Y., Toyama, K.: Evaluation scheme of focal translation for Japanese partially amended statutes. In: Proceedings of the 8th Workshop on Asian Translation (WAT2021), pp. 124–132 (2021)
Acknowledgments
This work was partly supported by JSPS KAKENHI Grant Number 21H03772.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yamakoshi, T., Ogawa, Y., Toyama, K. (2023). Differential-Aware Transformer for Partially Amended Sentence Translation. In: Takama, Y., Yada, K., Satoh, K., Arai, S. (eds) New Frontiers in Artificial Intelligence. JSAI-isAI 2022. Lecture Notes in Computer Science(), vol 13859. Springer, Cham. https://doi.org/10.1007/978-3-031-29168-5_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-29168-5_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-29167-8
Online ISBN: 978-3-031-29168-5
eBook Packages: Computer ScienceComputer Science (R0)