Abstract
Character-level translation has been proved to be able to achieve preferable translation quality without explicit segmentation, but training a character-level model needs a lot of hardware resources. In this paper, we introduced two character-level translation models which are mid-gated model and multi-attention model for Japanese-English translation. We showed that the mid-gated model achieved the better performance with respect to BLEU scores. We also showed that a relatively narrow beam of width 4 or 5 was sufficient for the mid-gated model. As for unknown words, we showed that the mid-gated model could somehow translate the one containing Katakana by coining out a close word. We also showed that the model managed to produce tolerable results for heavily noised sentences, even though the model was trained with the dataset without noise.- Anthology ID:
- D19-5202
- Volume:
- Proceedings of the 6th Workshop on Asian Translation
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Venue:
- WAT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 36–44
- Language:
- URL:
- https://aclanthology.org/D19-5202
- DOI:
- 10.18653/v1/D19-5202
- Cite (ACL):
- Jinan Dai and Kazunori Yamaguchi. 2019. Compact and Robust Models for Japanese-English Character-level Machine Translation. In Proceedings of the 6th Workshop on Asian Translation, pages 36–44, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Compact and Robust Models for Japanese-English Character-level Machine Translation (Dai & Yamaguchi, WAT 2019)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/D19-5202.pdf