@inproceedings{xie-etal-2022-string,
title = "String Editing Based {C}hinese Grammatical Error Diagnosis",
author = "Xie, Haihua and
Lyu, Xiaoqing and
Chen, Xuefei",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.474",
pages = "5335--5344",
abstract = "Chinese Grammatical Error Diagnosis (CGED) suffers the problems of numerous types of grammatical errors and insufficiency of training data. In this paper, we propose a string editing based CGED model that requires less training data by using a unified workflow to handle various types of grammatical errors. Two measures are proposed in our model to enhance the performance of CGED. First, the detection and correction of grammatical errors are divided into different stages. In the stage of error detection, the model only outputs the types of grammatical errors so that the tag vocabulary size is significantly reduced compared with other string editing based models. Secondly, the correction of some grammatical errors is converted to the task of masked character inference, which has plenty of training data and mature solutions. Experiments on datasets of NLPTEA-CGED demonstrate that our model outperforms other CGED models in many aspects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2022-string">
<titleInfo>
<title>String Editing Based Chinese Grammatical Error Diagnosis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haihua</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoqing</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuefei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Chinese Grammatical Error Diagnosis (CGED) suffers the problems of numerous types of grammatical errors and insufficiency of training data. In this paper, we propose a string editing based CGED model that requires less training data by using a unified workflow to handle various types of grammatical errors. Two measures are proposed in our model to enhance the performance of CGED. First, the detection and correction of grammatical errors are divided into different stages. In the stage of error detection, the model only outputs the types of grammatical errors so that the tag vocabulary size is significantly reduced compared with other string editing based models. Secondly, the correction of some grammatical errors is converted to the task of masked character inference, which has plenty of training data and mature solutions. Experiments on datasets of NLPTEA-CGED demonstrate that our model outperforms other CGED models in many aspects.</abstract>
<identifier type="citekey">xie-etal-2022-string</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.474</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5335</start>
<end>5344</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T String Editing Based Chinese Grammatical Error Diagnosis
%A Xie, Haihua
%A Lyu, Xiaoqing
%A Chen, Xuefei
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F xie-etal-2022-string
%X Chinese Grammatical Error Diagnosis (CGED) suffers the problems of numerous types of grammatical errors and insufficiency of training data. In this paper, we propose a string editing based CGED model that requires less training data by using a unified workflow to handle various types of grammatical errors. Two measures are proposed in our model to enhance the performance of CGED. First, the detection and correction of grammatical errors are divided into different stages. In the stage of error detection, the model only outputs the types of grammatical errors so that the tag vocabulary size is significantly reduced compared with other string editing based models. Secondly, the correction of some grammatical errors is converted to the task of masked character inference, which has plenty of training data and mature solutions. Experiments on datasets of NLPTEA-CGED demonstrate that our model outperforms other CGED models in many aspects.
%U https://aclanthology.org/2022.coling-1.474
%P 5335-5344
Markdown (Informal)
[String Editing Based Chinese Grammatical Error Diagnosis](https://aclanthology.org/2022.coling-1.474) (Xie et al., COLING 2022)
ACL
- Haihua Xie, Xiaoqing Lyu, and Xuefei Chen. 2022. String Editing Based Chinese Grammatical Error Diagnosis. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5335–5344, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.