@inproceedings{liang-etal-2020-bert,
title = "{BERT} Enhanced Neural Machine Translation and Sequence Tagging Model for {C}hinese Grammatical Error Diagnosis",
author = "Liang, Deng and
Zheng, Chen and
Guo, Lei and
Cui, Xin and
Xiong, Xiuzhang and
Rong, Hengqiao and
Dong, Jinpeng",
editor = "YANG, Erhong and
XUN, Endong and
ZHANG, Baolin and
RAO, Gaoqi",
booktitle = "Proceedings of the 6th Workshop on Natural Language Processing Techniques for Educational Applications",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlptea-1.8/",
doi = "10.18653/v1/2020.nlptea-1.8",
pages = "57--66",
abstract = "This paper presents the UNIPUS-Flaubert team`s hybrid system for the NLPTEA 2020 shared task of Chinese Grammatical Error Diagnosis (CGED). As a challenging NLP task, CGED has attracted increasing attention recently and has not yet fully benefited from the powerful pre-trained BERT-based models. We explore this by experimenting with three types of models. The position-tagging models and correction-tagging models are sequence tagging models fine-tuned on pre-trained BERT-based models, where the former focuses on detecting, positioning and classifying errors, and the latter aims at correcting errors. We also utilize rich representations from BERT-based models by transferring the BERT-fused models to the correction task, and further improve the performance by pre-training on a vast size of unsupervised synthetic data. To the best of our knowledge, we are the first to introduce and transfer the BERT-fused NMT model and sequence tagging model into the Chinese Grammatical Error Correction field. Our work achieved the second highest F1 score at the detecting errors, the best F1 score at correction top1 subtask and the second highest F1 score at correction top3 subtask."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2020-bert">
<titleInfo>
<title>BERT Enhanced Neural Machine Translation and Sequence Tagging Model for Chinese Grammatical Error Diagnosis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deng</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiuzhang</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengqiao</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinpeng</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Natural Language Processing Techniques for Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erhong</namePart>
<namePart type="family">YANG</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Endong</namePart>
<namePart type="family">XUN</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baolin</namePart>
<namePart type="family">ZHANG</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">RAO</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the UNIPUS-Flaubert team‘s hybrid system for the NLPTEA 2020 shared task of Chinese Grammatical Error Diagnosis (CGED). As a challenging NLP task, CGED has attracted increasing attention recently and has not yet fully benefited from the powerful pre-trained BERT-based models. We explore this by experimenting with three types of models. The position-tagging models and correction-tagging models are sequence tagging models fine-tuned on pre-trained BERT-based models, where the former focuses on detecting, positioning and classifying errors, and the latter aims at correcting errors. We also utilize rich representations from BERT-based models by transferring the BERT-fused models to the correction task, and further improve the performance by pre-training on a vast size of unsupervised synthetic data. To the best of our knowledge, we are the first to introduce and transfer the BERT-fused NMT model and sequence tagging model into the Chinese Grammatical Error Correction field. Our work achieved the second highest F1 score at the detecting errors, the best F1 score at correction top1 subtask and the second highest F1 score at correction top3 subtask.</abstract>
<identifier type="citekey">liang-etal-2020-bert</identifier>
<identifier type="doi">10.18653/v1/2020.nlptea-1.8</identifier>
<location>
<url>https://aclanthology.org/2020.nlptea-1.8/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>57</start>
<end>66</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERT Enhanced Neural Machine Translation and Sequence Tagging Model for Chinese Grammatical Error Diagnosis
%A Liang, Deng
%A Zheng, Chen
%A Guo, Lei
%A Cui, Xin
%A Xiong, Xiuzhang
%A Rong, Hengqiao
%A Dong, Jinpeng
%Y YANG, Erhong
%Y XUN, Endong
%Y ZHANG, Baolin
%Y RAO, Gaoqi
%S Proceedings of the 6th Workshop on Natural Language Processing Techniques for Educational Applications
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F liang-etal-2020-bert
%X This paper presents the UNIPUS-Flaubert team‘s hybrid system for the NLPTEA 2020 shared task of Chinese Grammatical Error Diagnosis (CGED). As a challenging NLP task, CGED has attracted increasing attention recently and has not yet fully benefited from the powerful pre-trained BERT-based models. We explore this by experimenting with three types of models. The position-tagging models and correction-tagging models are sequence tagging models fine-tuned on pre-trained BERT-based models, where the former focuses on detecting, positioning and classifying errors, and the latter aims at correcting errors. We also utilize rich representations from BERT-based models by transferring the BERT-fused models to the correction task, and further improve the performance by pre-training on a vast size of unsupervised synthetic data. To the best of our knowledge, we are the first to introduce and transfer the BERT-fused NMT model and sequence tagging model into the Chinese Grammatical Error Correction field. Our work achieved the second highest F1 score at the detecting errors, the best F1 score at correction top1 subtask and the second highest F1 score at correction top3 subtask.
%R 10.18653/v1/2020.nlptea-1.8
%U https://aclanthology.org/2020.nlptea-1.8/
%U https://doi.org/10.18653/v1/2020.nlptea-1.8
%P 57-66
Markdown (Informal)
[BERT Enhanced Neural Machine Translation and Sequence Tagging Model for Chinese Grammatical Error Diagnosis](https://aclanthology.org/2020.nlptea-1.8/) (Liang et al., NLP-TEA 2020)
ACL