Log In Sign Up

Shallow-to-Deep Training for Neural Machine Translation

by   Bei Li, et al.

Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why deep models help NMT is an open question. In this paper, we investigate the behavior of a well-tuned deep Transformer system. We find that stacking layers is helpful in improving the representation ability of NMT models and adjacent layers perform similarly. This inspires us to develop a shallow-to-deep training method that learns deep models by stacking shallow models. In this way, we successfully train a Transformer system with a 54-layer encoder. Experimental results on WMT'16 English-German and WMT'14 English-French translation tasks show that it is 1.4 × faster than training from scratch, and achieves a BLEU score of 30.33 and 43.29 on two tasks. The code is publicly available at


page 1

page 2

page 3

page 4


Very Deep Transformers for Neural Machine Translation

We explore the application of very deep Transformer models for Neural Ma...

Learning Light-Weight Translation Models from Deep Transformer

Recently, deep models have shown tremendous improvements in neural machi...

Multiscale Collaborative Deep Models for Neural Machine Translation

Recent evidence reveals that Neural Machine Translation (NMT) models wit...

Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models

Deep encoders have been proven to be effective in improving neural machi...

Training Deeper Neural Machine Translation Models with Transparent Attention

While current state-of-the-art NMT models, such as RNN seq2seq and Trans...

The NiuTrans System for WNGT 2020 Efficiency Task

This paper describes the submissions of the NiuTrans Team to the WNGT 20...

Multi-layer Representation Fusion for Neural Machine Translation

Neural machine translation systems require a number of stacked layers fo...