Abstract
In this paper we describe our neural machine translation (NMT) systems for Japanese↔English translation which we submitted to the translation robustness task. We focused on leveraging transfer learning via fine tuning to improve translation quality. We used a fairly well established domain adaptation technique called Mixed Fine Tuning (MFT) (Chu et. al., 2017) to improve translation quality for Japanese↔English. We also trained bi-directional NMT models instead of uni-directional ones as the former are known to be quite robust, especially in low-resource scenarios. However, given the noisy nature of the in-domain training data, the improvements we obtained are rather modest.- Anthology ID:
- W19-5362
- Volume:
- Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Marco Turchi, Karin Verspoor
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 533–536
- Language:
- URL:
- https://aclanthology.org/W19-5362
- DOI:
- 10.18653/v1/W19-5362
- Cite (ACL):
- Raj Dabre and Eiichiro Sumita. 2019. NICT’s Supervised Neural Machine Translation Systems for the WMT19 Translation Robustness Task. In Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pages 533–536, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- NICT’s Supervised Neural Machine Translation Systems for the WMT19 Translation Robustness Task (Dabre & Sumita, WMT 2019)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/W19-5362.pdf
- Data
- MTNT