Abstract
This paper describes multimodal machine translation systems developed jointly by Oregon State University and Baidu Research for WMT 2018 Shared Task on multimodal translation. In this paper, we introduce a simple approach to incorporate image information by feeding image features to the decoder side. We also explore different sequence level training methods including scheduled sampling and reinforcement learning which lead to substantial improvements. Our systems ensemble several models using different architectures and training methods and achieve the best performance for three subtasks: En-De and En-Cs in task 1 and (En+De+Fr)-Cs task 1B.- Anthology ID:
- W18-6443
- Volume:
- Proceedings of the Third Conference on Machine Translation: Shared Task Papers
- Month:
- October
- Year:
- 2018
- Address:
- Belgium, Brussels
- Editors:
- Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Lucia Specia, Marco Turchi, Karin Verspoor
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 632–636
- Language:
- URL:
- https://aclanthology.org/W18-6443
- DOI:
- 10.18653/v1/W18-6443
- Cite (ACL):
- Renjie Zheng, Yilin Yang, Mingbo Ma, and Liang Huang. 2018. Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 632–636, Belgium, Brussels. Association for Computational Linguistics.
- Cite (Informal):
- Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report (Zheng et al., WMT 2018)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/W18-6443.pdf