2019 ACL ACL 2019

Tilde’s Machine Translation Systems for WMT 2019

Abstract

AbstractThe paper describes the development process of Tilde’s NMT systems for the WMT 2019 shared task on news translation. We trained systems for the English-Lithuanian and Lithuanian-English translation directions in constrained and unconstrained tracks. We build upon the best methods of the previous year’s competition and combine them with recent advancements in the field. We also present a new method to ensure source domain adherence in back-translated data. Our systems achieved a shared first place in human evaluation.

🌉 Interdisciplinary Bridge — Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — domain adherence
🐣 Hot Topic Early Bird — low-resource language
🐝 Cross-Pollinator — Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Speech & Audio