2018
EMNLP
EMNLP 2018
Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report
Abstract
AbstractThis 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.
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Deep Learning and Machine Learning and Natural Language Processing and Reinforcement Learning
🧭
Keyword Pioneer
— sequence level training
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Artificial Intelligence > Core AI > Multimodal Learning
Natural Language Processing > Applications > Machine Translation
Reinforcement Learning > Methods > Deep RL
Machine Learning > Learning Types > Reinforcement Learning
Natural Language Processing > Generation > Machine Translation
Machine Learning > Learning Types > Multi-Modal Learning
Deep Learning > Models > Transformers
Deep Learning > Learning Types > Multi-Modal Learning