← Back to papers
2020 EMNLP EMNLP 2020

Tencent Neural Machine Translation Systems for the WMT20 News Translation Task

Abstract

AbstractThis paper describes Tencent Neural Machine Translation systems for the WMT 2020 news translation tasks. We participate in the shared news translation task on English ↔ Chinese and English → German language pairs. Our systems are built on deep Transformer and several data augmentation methods. We propose a boosted in-domain finetuning method to improve single models. Ensemble is used to combine single models and we propose an iterative transductive ensemble method which can further improve the translation performance based on the ensemble results. We achieve a BLEU score of 36.8 and the highest chrF score of 0.648 on Chinese → English task.

🌉 Interdisciplinary Bridge — Deep Learning and Natural Language Processing
🧭 Keyword Pioneer — boosted in-domain finetuning
🐝 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

Shuangzhi Wu , Xing Wang , Longyue Wang , Fangxu Liu , jun xie , Zhaopeng Tu , Shuming Shi , Mu Li

Topics

Natural Language Processing > Applications > Machine Translation Natural Language Processing > Generation > Machine Translation Deep Learning > Models > Transformers Deep Learning > Learning Types > Transfer Learning Deep Learning > Learning Types > Ensemble Learning

Keywords

ensemble learning data augmentation neural machine translation ensemble method deep transformer in-domain fine-tuning boosted in-domain finetuning iterative transductive ensemble
Download PDF

Related papers

Fast semantic parsing with well-typedness guarantees 2020
Detecting Objectifying Language in Online Professor Reviews 2020
Analogous Process Structure Induction for Sub-event Sequence Prediction 2020
Aspect Sentiment Classification with Aspect-Specific Opinion Spans 2020
Robust and Interpretable Grounding of Spatial References with Relation Networks 2020