@inproceedings{wang-etal-2020-combining-resnet,
title = "Combining {R}es{N}et and Transformer for {C}hinese Grammatical Error Diagnosis",
author = "Wang, Shaolei and
Wang, Baoxin and
Gong, Jiefu and
Wang, Zhongyuan and
Hu, Xiao and
Duan, Xingyi and
Shen, Zizhuo and
Yue, Gang and
Fu, Ruiji and
Wu, Dayong and
Che, Wanxiang and
Wang, Shijin and
Hu, Guoping and
Liu, Ting",
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-1.5/",
doi = "10.18653/v1/2020.nlptea-1.5",
pages = "36--43",
abstract = "Grammatical error diagnosis is an important task in natural language processing. This paper introduces our system at NLPTEA-2020 Task: Chinese Grammatical Error Diagnosis (CGED). CGED aims to diagnose four types of grammatical errors which are missing words (M), redundant words (R), bad word selection (S) and disordered words (W). Our system is built on the model of multi-layer bidirectional transformer encoder and ResNet is integrated into the encoder to improve the performance. We also explore two ensemble strategies including weighted averaging and stepwise ensemble selection from libraries of models to improve the performance of single model. In official evaluation, our system obtains the highest F1 scores at identification level and position level. We also recommend error corrections for specific error types and achieve the second highest F1 score at correction level."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2020-combining-resnet">
<titleInfo>
<title>Combining ResNet and Transformer for Chinese Grammatical Error Diagnosis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shaolei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baoxin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiefu</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingyi</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zizhuo</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gang</namePart>
<namePart type="family">Yue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiji</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayong</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoping</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</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>Grammatical error diagnosis is an important task in natural language processing. This paper introduces our system at NLPTEA-2020 Task: Chinese Grammatical Error Diagnosis (CGED). CGED aims to diagnose four types of grammatical errors which are missing words (M), redundant words (R), bad word selection (S) and disordered words (W). Our system is built on the model of multi-layer bidirectional transformer encoder and ResNet is integrated into the encoder to improve the performance. We also explore two ensemble strategies including weighted averaging and stepwise ensemble selection from libraries of models to improve the performance of single model. In official evaluation, our system obtains the highest F1 scores at identification level and position level. We also recommend error corrections for specific error types and achieve the second highest F1 score at correction level.</abstract>
<identifier type="citekey">wang-etal-2020-combining-resnet</identifier>
<identifier type="doi">10.18653/v1/2020.nlptea-1.5</identifier>
<location>
<url>https://aclanthology.org/2020.nlptea-1.5/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>36</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combining ResNet and Transformer for Chinese Grammatical Error Diagnosis
%A Wang, Shaolei
%A Wang, Baoxin
%A Gong, Jiefu
%A Wang, Zhongyuan
%A Hu, Xiao
%A Duan, Xingyi
%A Shen, Zizhuo
%A Yue, Gang
%A Fu, Ruiji
%A Wu, Dayong
%A Che, Wanxiang
%A Wang, Shijin
%A Hu, Guoping
%A Liu, Ting
%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 wang-etal-2020-combining-resnet
%X Grammatical error diagnosis is an important task in natural language processing. This paper introduces our system at NLPTEA-2020 Task: Chinese Grammatical Error Diagnosis (CGED). CGED aims to diagnose four types of grammatical errors which are missing words (M), redundant words (R), bad word selection (S) and disordered words (W). Our system is built on the model of multi-layer bidirectional transformer encoder and ResNet is integrated into the encoder to improve the performance. We also explore two ensemble strategies including weighted averaging and stepwise ensemble selection from libraries of models to improve the performance of single model. In official evaluation, our system obtains the highest F1 scores at identification level and position level. We also recommend error corrections for specific error types and achieve the second highest F1 score at correction level.
%R 10.18653/v1/2020.nlptea-1.5
%U https://aclanthology.org/2020.nlptea-1.5/
%U https://doi.org/10.18653/v1/2020.nlptea-1.5
%P 36-43
Markdown (Informal)
[Combining ResNet and Transformer for Chinese Grammatical Error Diagnosis](https://aclanthology.org/2020.nlptea-1.5/) (Wang et al., NLP-TEA 2020)
ACL
- Shaolei Wang, Baoxin Wang, Jiefu Gong, Zhongyuan Wang, Xiao Hu, Xingyi Duan, Zizhuo Shen, Gang Yue, Ruiji Fu, Dayong Wu, Wanxiang Che, Shijin Wang, Guoping Hu, and Ting Liu. 2020. Combining ResNet and Transformer for Chinese Grammatical Error Diagnosis. In Proceedings of the 6th Workshop on Natural Language Processing Techniques for Educational Applications, pages 36–43, Suzhou, China. Association for Computational Linguistics.