Abstract
In this year, we participated in four translation subtasks at WAT 2017. Our model structure is quite simple but we used it with well-tuned hyper-parameters, leading to a significant improvement compared to the previous state-of-the-art system. We also tried to make use of the unreliable part of the provided parallel corpus by back-translating and making a synthetic corpus. Our submitted system achieved the new state-of-the-art performance in terms of the BLEU score, as well as human evaluation.- Anthology ID:
- W17-5706
- Volume:
- Proceedings of the 4th Workshop on Asian Translation (WAT2017)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Toshiaki Nakazawa, Isao Goto
- Venue:
- WAT
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 89–94
- Language:
- URL:
- https://aclanthology.org/W17-5706
- DOI:
- Cite (ACL):
- Makoto Morishita, Jun Suzuki, and Masaaki Nagata. 2017. NTT Neural Machine Translation Systems at WAT 2017. In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pages 89–94, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- NTT Neural Machine Translation Systems at WAT 2017 (Morishita et al., WAT 2017)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/W17-5706.pdf
- Data
- ASPEC