2018 EMNLP EMNLP 2018

Neural Machine Translation with the Transformer and Multi-Source Romance Languages for the Biomedical WMT 2018 task

Abstract

AbstractThe Transformer architecture has become the state-of-the-art in Machine Translation. This model, which relies on attention-based mechanisms, has outperformed previous neural machine translation architectures in several tasks. In this system description paper, we report details of training neural machine translation with multi-source Romance languages with the Transformer model and in the evaluation frame of the biomedical WMT 2018 task. Using multi-source languages from the same family allows improvements of over 6 BLEU points.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — romance language
🐣 Hot Topic Early Bird — biomedical text
🐝 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