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.
@article{arxiv.1808.10592,
title = {Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report},
author = {Renjie Zheng and Yilin Yang and Mingbo Ma and Liang Huang},
journal= {arXiv preprint arXiv:1808.10592},
year = {2018}
}