2020
EMNLP
EMNLP 2020
The Volctrans Machine Translation System for WMT20
Abstract
AbstractThis paper describes our submission systems for VolcTrans for WMT20 shared news translation task. We participated in 8 translation directions. Our basic systems are based on Transformer (CITATION), into which we also employed new architectures (bigger or deeper Transformers, dynamic convolution). The final systems include text pre-process, subword(a.k.a. BPE(CITATION)), baseline model training, iterative back-translation, model ensemble, knowledge distillation and multilingual pre-training.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Natural Language Processing
Authors
Topics
Machine Learning > Application Areas > Knowledge Distillation
Machine Learning > Application Areas > Model Merging
Deep Learning > Architectures > Transformers
Natural Language Processing > Applications > Machine Translation
Machine Learning > Learning Types > Transfer Learning
Deep Learning > Learning Types > Transfer Learning