@inproceedings{yang-etal-2021-smart,
title = "Smart-Start Decoding for Neural Machine Translation",
author = "Yang, Jian and
Ma, Shuming and
Zhang, Dongdong and
Wan, Juncheng and
Li, Zhoujun and
Zhou, Ming",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.312",
doi = "10.18653/v1/2021.naacl-main.312",
pages = "3982--3988",
abstract = "Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left. In this work, we propose a novel method that breaks up the limitation of these decoding orders, called Smart-Start decoding. More specifically, our method first predicts a median word. It starts to decode the words on the right side of the median word and then generates words on the left. We evaluate the proposed Smart-Start decoding method on three datasets. Experimental results show that the proposed method can significantly outperform strong baseline models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2021-smart">
<titleInfo>
<title>Smart-Start Decoding for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongdong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juncheng</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhoujun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left. In this work, we propose a novel method that breaks up the limitation of these decoding orders, called Smart-Start decoding. More specifically, our method first predicts a median word. It starts to decode the words on the right side of the median word and then generates words on the left. We evaluate the proposed Smart-Start decoding method on three datasets. Experimental results show that the proposed method can significantly outperform strong baseline models.</abstract>
<identifier type="citekey">yang-etal-2021-smart</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.312</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.312</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>3982</start>
<end>3988</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Smart-Start Decoding for Neural Machine Translation
%A Yang, Jian
%A Ma, Shuming
%A Zhang, Dongdong
%A Wan, Juncheng
%A Li, Zhoujun
%A Zhou, Ming
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F yang-etal-2021-smart
%X Most current neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to-left. In this work, we propose a novel method that breaks up the limitation of these decoding orders, called Smart-Start decoding. More specifically, our method first predicts a median word. It starts to decode the words on the right side of the median word and then generates words on the left. We evaluate the proposed Smart-Start decoding method on three datasets. Experimental results show that the proposed method can significantly outperform strong baseline models.
%R 10.18653/v1/2021.naacl-main.312
%U https://aclanthology.org/2021.naacl-main.312
%U https://doi.org/10.18653/v1/2021.naacl-main.312
%P 3982-3988
Markdown (Informal)
[Smart-Start Decoding for Neural Machine Translation](https://aclanthology.org/2021.naacl-main.312) (Yang et al., NAACL 2021)
ACL
- Jian Yang, Shuming Ma, Dongdong Zhang, Juncheng Wan, Zhoujun Li, and Ming Zhou. 2021. Smart-Start Decoding for Neural Machine Translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3982–3988, Online. Association for Computational Linguistics.