@inproceedings{chen-etal-2022-synchronous,
title = "Synchronous Refinement for Neural Machine Translation",
author = "Chen, Kehai and
Utiyama, Masao and
Sumita, Eiichiro and
Wang, Rui and
Zhang, Min",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.235",
doi = "10.18653/v1/2022.findings-acl.235",
pages = "2986--2996",
abstract = "Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner. However, the auto-regressive decoder faces a deep-rooted $one$-$pass$ issue whereby each generated word is considered as one element of the final output regardless of whether it is correct or not. These generated wrong words further constitute the target historical context to affect the generation of subsequent target words. This paper proposes a novel synchronous refinement method to revise potential errors in the generated words by considering part of the target future context. Particularly, the proposed approach allows the auto-regressive decoder to refine the previously generated target words and generate the next target word synchronously. The experimental results on three widely-used machine translation tasks demonstrated the effectiveness of the proposed approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-synchronous">
<titleInfo>
<title>Synchronous Refinement for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kehai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner. However, the auto-regressive decoder faces a deep-rooted one-pass issue whereby each generated word is considered as one element of the final output regardless of whether it is correct or not. These generated wrong words further constitute the target historical context to affect the generation of subsequent target words. This paper proposes a novel synchronous refinement method to revise potential errors in the generated words by considering part of the target future context. Particularly, the proposed approach allows the auto-regressive decoder to refine the previously generated target words and generate the next target word synchronously. The experimental results on three widely-used machine translation tasks demonstrated the effectiveness of the proposed approach.</abstract>
<identifier type="citekey">chen-etal-2022-synchronous</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.235</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.235</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2986</start>
<end>2996</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synchronous Refinement for Neural Machine Translation
%A Chen, Kehai
%A Utiyama, Masao
%A Sumita, Eiichiro
%A Wang, Rui
%A Zhang, Min
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F chen-etal-2022-synchronous
%X Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner. However, the auto-regressive decoder faces a deep-rooted one-pass issue whereby each generated word is considered as one element of the final output regardless of whether it is correct or not. These generated wrong words further constitute the target historical context to affect the generation of subsequent target words. This paper proposes a novel synchronous refinement method to revise potential errors in the generated words by considering part of the target future context. Particularly, the proposed approach allows the auto-regressive decoder to refine the previously generated target words and generate the next target word synchronously. The experimental results on three widely-used machine translation tasks demonstrated the effectiveness of the proposed approach.
%R 10.18653/v1/2022.findings-acl.235
%U https://aclanthology.org/2022.findings-acl.235
%U https://doi.org/10.18653/v1/2022.findings-acl.235
%P 2986-2996
Markdown (Informal)
[Synchronous Refinement for Neural Machine Translation](https://aclanthology.org/2022.findings-acl.235) (Chen et al., Findings 2022)
ACL
- Kehai Chen, Masao Utiyama, Eiichiro Sumita, Rui Wang, and Min Zhang. 2022. Synchronous Refinement for Neural Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2986–2996, Dublin, Ireland. Association for Computational Linguistics.