@inproceedings{hu-etal-2018-ling,
title = "Ling@{CASS} Solution to the {NLP}-{TEA} {CGED} Shared Task 2018",
author = "Hu, Qinan and
Zhang, Yongwei and
Liu, Fang and
Gu, Yueguo",
editor = "Tseng, Yuen-Hsien and
Chen, Hsin-Hsi and
Ng, Vincent and
Komachi, Mamoru",
booktitle = "Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3709",
doi = "10.18653/v1/W18-3709",
pages = "70--76",
abstract = "In this study, we employ the sequence to sequence learning to model the task of grammar error correction. The system takes potentially erroneous sentences as inputs, and outputs correct sentences. To breakthrough the bottlenecks of very limited size of manually labeled data, we adopt a semi-supervised approach. Specifically, we adapt correct sentences written by native Chinese speakers to generate pseudo grammatical errors made by learners of Chinese as a second language. We use the pseudo data to pre-train the model, and the CGED data to fine-tune it. Being aware of the significance of precision in a grammar error correction system in real scenarios, we use ensembles to boost precision. When using inputs as simple as Chinese characters, the ensembled system achieves a precision at 86.56{\%} in the detection of erroneous sentences, and a precision at 51.53{\%} in the correction of errors of Selection and Missing types.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2018-ling">
<titleInfo>
<title>Ling@CASS Solution to the NLP-TEA CGED Shared Task 2018</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qinan</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongwei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yueguo</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuen-Hsien</namePart>
<namePart type="family">Tseng</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">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study, we employ the sequence to sequence learning to model the task of grammar error correction. The system takes potentially erroneous sentences as inputs, and outputs correct sentences. To breakthrough the bottlenecks of very limited size of manually labeled data, we adopt a semi-supervised approach. Specifically, we adapt correct sentences written by native Chinese speakers to generate pseudo grammatical errors made by learners of Chinese as a second language. We use the pseudo data to pre-train the model, and the CGED data to fine-tune it. Being aware of the significance of precision in a grammar error correction system in real scenarios, we use ensembles to boost precision. When using inputs as simple as Chinese characters, the ensembled system achieves a precision at 86.56% in the detection of erroneous sentences, and a precision at 51.53% in the correction of errors of Selection and Missing types.</abstract>
<identifier type="citekey">hu-etal-2018-ling</identifier>
<identifier type="doi">10.18653/v1/W18-3709</identifier>
<location>
<url>https://aclanthology.org/W18-3709</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>70</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ling@CASS Solution to the NLP-TEA CGED Shared Task 2018
%A Hu, Qinan
%A Zhang, Yongwei
%A Liu, Fang
%A Gu, Yueguo
%Y Tseng, Yuen-Hsien
%Y Chen, Hsin-Hsi
%Y Ng, Vincent
%Y Komachi, Mamoru
%S Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F hu-etal-2018-ling
%X In this study, we employ the sequence to sequence learning to model the task of grammar error correction. The system takes potentially erroneous sentences as inputs, and outputs correct sentences. To breakthrough the bottlenecks of very limited size of manually labeled data, we adopt a semi-supervised approach. Specifically, we adapt correct sentences written by native Chinese speakers to generate pseudo grammatical errors made by learners of Chinese as a second language. We use the pseudo data to pre-train the model, and the CGED data to fine-tune it. Being aware of the significance of precision in a grammar error correction system in real scenarios, we use ensembles to boost precision. When using inputs as simple as Chinese characters, the ensembled system achieves a precision at 86.56% in the detection of erroneous sentences, and a precision at 51.53% in the correction of errors of Selection and Missing types.
%R 10.18653/v1/W18-3709
%U https://aclanthology.org/W18-3709
%U https://doi.org/10.18653/v1/W18-3709
%P 70-76
Markdown (Informal)
[Ling@CASS Solution to the NLP-TEA CGED Shared Task 2018](https://aclanthology.org/W18-3709) (Hu et al., NLP-TEA 2018)
ACL
- Qinan Hu, Yongwei Zhang, Fang Liu, and Yueguo Gu. 2018. Ling@CASS Solution to the NLP-TEA CGED Shared Task 2018. In Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications, pages 70–76, Melbourne, Australia. Association for Computational Linguistics.