← Back to papers
2022 EMNLP EMNLP 2022

Improved Data Augmentation for Translation Suggestion

Abstract

AbstractTranslation suggestion (TS) models are used to automatically provide alternative suggestions for incorrect spans in sentences generated by machine translation. This paper introduces the system used in our submission to the WMT’22 Translation Suggestion shared task. Our system is based on the ensemble of different translation architectures, including Transformer, SA-Transformer, and DynamicConv. We use three strategies to construct synthetic data from parallel corpora to compensate for the lack of supervised data. In addition, we introduce a multi-phase pre-training strategy, adding an additional pre-training phase with in-domain data. We rank second and third on the English-German and English-Chinese bidirectional tasks, respectively.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Deep Learning and Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — multi-phase pre-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

Hongxiao Zhang , Siyu Lai , Songming Zhang , Hui Huang , Yufeng Chen , Jinan Xu , Jian Liu

Topics

Machine Learning > Application Areas > Data Augmentation Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation Natural Language Processing > Generation > Machine Translation Machine Learning > Learning Types > Data Augmentation Deep Learning > Techniques > Transfer Learning Artificial Intelligence > Core AI > Natural Language Processing Machine Learning > Learning Types > Machine Translation Deep Learning > Learning Types > Sequence Modeling

Keywords

transformer architecture ensemble learning data augmentation synthetic datum translation suggestion multi-phase pre-training ensemble translation
Download PDF

Related papers

Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport 2022
Generative Entity Typing with Curriculum Learning 2022
Towards Reinterpreting Neural Topic Models via Composite Activations 2022
Weakly Supervised Headline Dependency Parsing 2022
Cross-modal Transfer Between Vision and Language for Protest Detection 2022