@inproceedings{xu-etal-2019-erroneous,
title = "Erroneous data generation for Grammatical Error Correction",
author = "Xu, Shuyao and
Zhang, Jiehao and
Chen, Jin and
Qin, Long",
editor = "Yannakoudakis, Helen and
Kochmar, Ekaterina and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Zesch, Torsten",
booktitle = "Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4415",
doi = "10.18653/v1/W19-4415",
pages = "149--158",
abstract = "It has been demonstrated that the utilization of a monolingual corpus in neural Grammatical Error Correction (GEC) systems can significantly improve the system performance. The previous state-of-the-art neural GEC system is an ensemble of four Transformer models pretrained on a large amount of Wikipedia Edits. The Singsound GEC system follows a similar approach but is equipped with a sophisticated erroneous data generating component. Our system achieved an F0:5 of 66.61 in the BEA 2019 Shared Task: Grammatical Error Correction. With our novel erroneous data generating component, the Singsound neural GEC system yielded an M2 of 63.2 on the CoNLL-2014 benchmark (8.4{\%} relative improvement over the previous state-of-the-art system).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2019-erroneous">
<titleInfo>
<title>Erroneous data generation for Grammatical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuyao</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiehao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>It has been demonstrated that the utilization of a monolingual corpus in neural Grammatical Error Correction (GEC) systems can significantly improve the system performance. The previous state-of-the-art neural GEC system is an ensemble of four Transformer models pretrained on a large amount of Wikipedia Edits. The Singsound GEC system follows a similar approach but is equipped with a sophisticated erroneous data generating component. Our system achieved an F0:5 of 66.61 in the BEA 2019 Shared Task: Grammatical Error Correction. With our novel erroneous data generating component, the Singsound neural GEC system yielded an M2 of 63.2 on the CoNLL-2014 benchmark (8.4% relative improvement over the previous state-of-the-art system).</abstract>
<identifier type="citekey">xu-etal-2019-erroneous</identifier>
<identifier type="doi">10.18653/v1/W19-4415</identifier>
<location>
<url>https://aclanthology.org/W19-4415</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>149</start>
<end>158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Erroneous data generation for Grammatical Error Correction
%A Xu, Shuyao
%A Zhang, Jiehao
%A Chen, Jin
%A Qin, Long
%Y Yannakoudakis, Helen
%Y Kochmar, Ekaterina
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Zesch, Torsten
%S Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F xu-etal-2019-erroneous
%X It has been demonstrated that the utilization of a monolingual corpus in neural Grammatical Error Correction (GEC) systems can significantly improve the system performance. The previous state-of-the-art neural GEC system is an ensemble of four Transformer models pretrained on a large amount of Wikipedia Edits. The Singsound GEC system follows a similar approach but is equipped with a sophisticated erroneous data generating component. Our system achieved an F0:5 of 66.61 in the BEA 2019 Shared Task: Grammatical Error Correction. With our novel erroneous data generating component, the Singsound neural GEC system yielded an M2 of 63.2 on the CoNLL-2014 benchmark (8.4% relative improvement over the previous state-of-the-art system).
%R 10.18653/v1/W19-4415
%U https://aclanthology.org/W19-4415
%U https://doi.org/10.18653/v1/W19-4415
%P 149-158
Markdown (Informal)
[Erroneous data generation for Grammatical Error Correction](https://aclanthology.org/W19-4415) (Xu et al., BEA 2019)
ACL
- Shuyao Xu, Jiehao Zhang, Jin Chen, and Long Qin. 2019. Erroneous data generation for Grammatical Error Correction. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 149–158, Florence, Italy. Association for Computational Linguistics.