@inproceedings{li-etal-2020-shallow,
title = "Shallow-to-Deep Training for Neural Machine Translation",
author = "Li, Bei and
Wang, Ziyang and
Liu, Hui and
Jiang, Yufan and
Du, Quan and
Xiao, Tong and
Wang, Huizhen and
Zhu, Jingbo",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.72",
doi = "10.18653/v1/2020.emnlp-main.72",
pages = "995--1005",
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 \url{https://github.com/libeineu/SDT-Training}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-shallow">
<titleInfo>
<title>Shallow-to-Deep Training for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufan</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huizhen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">li-etal-2020-shallow</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.72</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.72</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>995</start>
<end>1005</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Shallow-to-Deep Training for Neural Machine Translation
%A Li, Bei
%A Wang, Ziyang
%A Liu, Hui
%A Jiang, Yufan
%A Du, Quan
%A Xiao, Tong
%A Wang, Huizhen
%A Zhu, Jingbo
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F li-etal-2020-shallow
%X 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.
%R 10.18653/v1/2020.emnlp-main.72
%U https://aclanthology.org/2020.emnlp-main.72
%U https://doi.org/10.18653/v1/2020.emnlp-main.72
%P 995-1005
Markdown (Informal)
[Shallow-to-Deep Training for Neural Machine Translation](https://aclanthology.org/2020.emnlp-main.72) (Li et al., EMNLP 2020)
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.