Shallow-to-Deep Training for Neural Machine Translation

Bei Li, Ziyang Wang, Hui Liu, Yufan Jiang, Quan Du, Tong Xiao, Huizhen Wang, Jingbo Zhu


Abstract
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 https://github.com/libeineu/SDT-Training.
Anthology ID:
2020.emnlp-main.72
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
995–1005
Language:
URL:
https://aclanthology.org/2020.emnlp-main.72
DOI:
10.18653/v1/2020.emnlp-main.72
Bibkey:
Cite (ACL):
Bei Li, Ziyang Wang, Hui Liu, Yufan Jiang, Quan Du, Tong Xiao, Huizhen Wang, and Jingbo Zhu. 2020. Shallow-to-Deep Training for Neural Machine Translation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 995–1005, Online. Association for Computational Linguistics.
Cite (Informal):
Shallow-to-Deep Training for Neural Machine Translation (Li et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.emnlp-main.72.pdf
Video:
 https://slideslive.com/38938655
Code
 libeineu/SDT-Training