Abstract
In this paper, we describe the NICT-2 neural machine translation system evaluated at WAT2017. This system uses multiple models as an ensemble and combines models with opposite decoding directions by reranking (called bi-directional reranking). In our experimental results on small data sets, the translation quality improved when the number of models was increased to 32 in total and did not saturate. In the experiments on large data sets, improvements of 1.59-3.32 BLEU points were achieved when six-model ensembles were combined by the bi-directional reranking.- Anthology ID:
- W17-5711
- 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:
- 127–134
- Language:
- URL:
- https://aclanthology.org/W17-5711
- DOI:
- Cite (ACL):
- Kenji Imamura and Eiichiro Sumita. 2017. Ensemble and Reranking: Using Multiple Models in the NICT-2 Neural Machine Translation System at WAT2017. In Proceedings of the 4th Workshop on Asian Translation (WAT2017), pages 127–134, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Ensemble and Reranking: Using Multiple Models in the NICT-2 Neural Machine Translation System at WAT2017 (Imamura & Sumita, WAT 2017)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/W17-5711.pdf