@inproceedings{lee-etal-2021-adaptation,
title = "Adaptation of Back-translation to Automatic Post-Editing for Synthetic Data Generation",
author = "Lee, WonKee and
Jung, Baikjin and
Shin, Jaehun and
Lee, Jong-Hyeok",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.322",
doi = "10.18653/v1/2021.eacl-main.322",
pages = "3685--3691",
abstract = "Automatic Post-Editing (APE) aims to correct errors in the output of a given machine translation (MT) system. Although data-driven approaches have become prevalent also in the APE task as in many other NLP tasks, there has been a lack of qualified training data due to the high cost of manual construction. eSCAPE, a synthetic APE corpus, has been widely used to alleviate the data scarcity, but it might not address genuine APE corpora{'}s characteristic that the post-edited sentence should be a minimally edited revision of the given MT output. Therefore, we propose two new methods of synthesizing additional MT outputs by adapting back-translation to the APE task, obtaining robust enlargements of the existing synthetic APE training dataset. Experimental results on the WMT English-German APE benchmarks demonstrate that our enlarged datasets are effective in improving APE performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2021-adaptation">
<titleInfo>
<title>Adaptation of Back-translation to Automatic Post-Editing for Synthetic Data Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">WonKee</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baikjin</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaehun</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong-Hyeok</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</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>Automatic Post-Editing (APE) aims to correct errors in the output of a given machine translation (MT) system. Although data-driven approaches have become prevalent also in the APE task as in many other NLP tasks, there has been a lack of qualified training data due to the high cost of manual construction. eSCAPE, a synthetic APE corpus, has been widely used to alleviate the data scarcity, but it might not address genuine APE corpora’s characteristic that the post-edited sentence should be a minimally edited revision of the given MT output. Therefore, we propose two new methods of synthesizing additional MT outputs by adapting back-translation to the APE task, obtaining robust enlargements of the existing synthetic APE training dataset. Experimental results on the WMT English-German APE benchmarks demonstrate that our enlarged datasets are effective in improving APE performance.</abstract>
<identifier type="citekey">lee-etal-2021-adaptation</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.322</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.322</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>3685</start>
<end>3691</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adaptation of Back-translation to Automatic Post-Editing for Synthetic Data Generation
%A Lee, WonKee
%A Jung, Baikjin
%A Shin, Jaehun
%A Lee, Jong-Hyeok
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F lee-etal-2021-adaptation
%X Automatic Post-Editing (APE) aims to correct errors in the output of a given machine translation (MT) system. Although data-driven approaches have become prevalent also in the APE task as in many other NLP tasks, there has been a lack of qualified training data due to the high cost of manual construction. eSCAPE, a synthetic APE corpus, has been widely used to alleviate the data scarcity, but it might not address genuine APE corpora’s characteristic that the post-edited sentence should be a minimally edited revision of the given MT output. Therefore, we propose two new methods of synthesizing additional MT outputs by adapting back-translation to the APE task, obtaining robust enlargements of the existing synthetic APE training dataset. Experimental results on the WMT English-German APE benchmarks demonstrate that our enlarged datasets are effective in improving APE performance.
%R 10.18653/v1/2021.eacl-main.322
%U https://aclanthology.org/2021.eacl-main.322
%U https://doi.org/10.18653/v1/2021.eacl-main.322
%P 3685-3691
Markdown (Informal)
[Adaptation of Back-translation to Automatic Post-Editing for Synthetic Data Generation](https://aclanthology.org/2021.eacl-main.322) (Lee et al., EACL 2021)
ACL