@inproceedings{fang-etal-2023-transgec,
title = "{T}rans{GEC}: Improving Grammatical Error Correction with Translationese",
author = "Fang, Tao and
Liu, Xuebo and
Wong, Derek F. and
Zhan, Runzhe and
Ding, Liang and
Chao, Lidia S. and
Tao, Dacheng and
Zhang, Min",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.223",
doi = "10.18653/v1/2023.findings-acl.223",
pages = "3614--3633",
abstract = "Data augmentation is an effective way to improve model performance of grammatical error correction (GEC). This paper identifies a critical side-effect of GEC data augmentation, which is due to the style discrepancy between the data used in GEC tasks (i.e., texts produced by non-native speakers) and data augmentation (i.e., native texts). To alleviate this issue, we propose to use an alternative data source, translationese (i.e., human-translated texts), as input for GEC data augmentation, which 1) is easier to obtain and usually has better quality than non-native texts, and 2) has a more similar style to non-native texts. Experimental results on the CoNLL14 and BEA19 English, NLPCC18 Chinese, Falko-MERLIN German, and RULEC-GEC Russian GEC benchmarks show that our approach consistently improves correction accuracy over strong baselines. Further analyses reveal that our approach is helpful for overcoming mainstream correction difficulties such as the corrections of frequent words, missing words, and substitution errors. Data, code, models and scripts are freely available at \url{https://github.com/NLP2CT/TransGEC}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-etal-2023-transgec">
<titleInfo>
<title>TransGEC: Improving Grammatical Error Correction with Translationese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuebo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runzhe</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Chao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dacheng</namePart>
<namePart type="family">Tao</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>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data augmentation is an effective way to improve model performance of grammatical error correction (GEC). This paper identifies a critical side-effect of GEC data augmentation, which is due to the style discrepancy between the data used in GEC tasks (i.e., texts produced by non-native speakers) and data augmentation (i.e., native texts). To alleviate this issue, we propose to use an alternative data source, translationese (i.e., human-translated texts), as input for GEC data augmentation, which 1) is easier to obtain and usually has better quality than non-native texts, and 2) has a more similar style to non-native texts. Experimental results on the CoNLL14 and BEA19 English, NLPCC18 Chinese, Falko-MERLIN German, and RULEC-GEC Russian GEC benchmarks show that our approach consistently improves correction accuracy over strong baselines. Further analyses reveal that our approach is helpful for overcoming mainstream correction difficulties such as the corrections of frequent words, missing words, and substitution errors. Data, code, models and scripts are freely available at https://github.com/NLP2CT/TransGEC.</abstract>
<identifier type="citekey">fang-etal-2023-transgec</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.223</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.223</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>3614</start>
<end>3633</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TransGEC: Improving Grammatical Error Correction with Translationese
%A Fang, Tao
%A Liu, Xuebo
%A Wong, Derek F.
%A Zhan, Runzhe
%A Ding, Liang
%A Chao, Lidia S.
%A Tao, Dacheng
%A Zhang, Min
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F fang-etal-2023-transgec
%X Data augmentation is an effective way to improve model performance of grammatical error correction (GEC). This paper identifies a critical side-effect of GEC data augmentation, which is due to the style discrepancy between the data used in GEC tasks (i.e., texts produced by non-native speakers) and data augmentation (i.e., native texts). To alleviate this issue, we propose to use an alternative data source, translationese (i.e., human-translated texts), as input for GEC data augmentation, which 1) is easier to obtain and usually has better quality than non-native texts, and 2) has a more similar style to non-native texts. Experimental results on the CoNLL14 and BEA19 English, NLPCC18 Chinese, Falko-MERLIN German, and RULEC-GEC Russian GEC benchmarks show that our approach consistently improves correction accuracy over strong baselines. Further analyses reveal that our approach is helpful for overcoming mainstream correction difficulties such as the corrections of frequent words, missing words, and substitution errors. Data, code, models and scripts are freely available at https://github.com/NLP2CT/TransGEC.
%R 10.18653/v1/2023.findings-acl.223
%U https://aclanthology.org/2023.findings-acl.223
%U https://doi.org/10.18653/v1/2023.findings-acl.223
%P 3614-3633
Markdown (Informal)
[TransGEC: Improving Grammatical Error Correction with Translationese](https://aclanthology.org/2023.findings-acl.223) (Fang et al., Findings 2023)
ACL
- Tao Fang, Xuebo Liu, Derek F. Wong, Runzhe Zhan, Liang Ding, Lidia S. Chao, Dacheng Tao, and Min Zhang. 2023. TransGEC: Improving Grammatical Error Correction with Translationese. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3614–3633, Toronto, Canada. Association for Computational Linguistics.