Abstract
In this paper, we describe our neural machine translation (NMT) system, which is based on the attention-based NMT and uses long short-term memories (LSTM) as RNN. We implemented beam search and ensemble decoding in the NMT system. The system was tested on the 4th Workshop on Asian Translation (WAT 2017) shared tasks. In our experiments, we participated in the scientific paper subtasks and attempted Japanese-English, English-Japanese, and Japanese-Chinese translation tasks. The experimental results showed that implementation of beam search and ensemble decoding can effectively improve the translation quality.- Anthology ID:
- W17-5716
- 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:
- 160–166
- Language:
- URL:
- https://aclanthology.org/W17-5716
- DOI:
- Cite (ACL):
- Yukio Matsumura and Mamoru Komachi. 2017. Tokyo Metropolitan University Neural Machine Translation System for WAT 2017. In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pages 160–166, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Tokyo Metropolitan University Neural Machine Translation System for WAT 2017 (Matsumura & Komachi, WAT 2017)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/W17-5716.pdf