@inproceedings{xie-etal-2020-ji,
title = "基于数据增强和多任务特征学习的中文语法错误检测方法({C}hinese Grammar Error Detection based on Data Enhancement and Multi-task Feature Learning)",
author = "Xie, Haihua and
Chen, Zhiyou and
Cheng, Jing and
Lyu, Xiaoqing and
Tang, Zhi",
editor = "Sun, Maosong and
Li, Sujian and
Zhang, Yue and
Liu, Yang",
booktitle = "Proceedings of the 19th Chinese National Conference on Computational Linguistics",
month = oct,
year = "2020",
address = "Haikou, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2020.ccl-1.71",
pages = "761--770",
abstract = "由于中文语法的复杂性,中文语法错误检测(CGED)的难度较大,而训练语料和相关研究的缺乏,使得CGED的效果还远达不到能够实用的程度。本文提出一种CGED模型,采用数据增强、预训练语言模型和基于语言学特征多任务学习的方式,弥补训练语料稀缺的不足。数据增强能够有效地扩充训练集,预训练语言模型蕴含丰富的语义信息有助于语法分析,基于语言学特征多任务学习对语言模型进行微调则可以使语言模型学习到跟语法错误检测相关的语言学特征。本文提出的方法在NLPTEA的CGED数据集进行测试,取得了优于其他模型的结果。",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2020-ji">
<titleInfo>
<title>基于数据增强和多任务特征学习的中文语法错误检测方法(Chinese Grammar Error Detection based on Data Enhancement and Multi-task Feature Learning)</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">Zhiyou</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Cheng</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">Zhi</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">Chinese</languageTerm>
<languageTerm type="code" authority="iso639-2b">chi</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Haikou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>由于中文语法的复杂性,中文语法错误检测(CGED)的难度较大,而训练语料和相关研究的缺乏,使得CGED的效果还远达不到能够实用的程度。本文提出一种CGED模型,采用数据增强、预训练语言模型和基于语言学特征多任务学习的方式,弥补训练语料稀缺的不足。数据增强能够有效地扩充训练集,预训练语言模型蕴含丰富的语义信息有助于语法分析,基于语言学特征多任务学习对语言模型进行微调则可以使语言模型学习到跟语法错误检测相关的语言学特征。本文提出的方法在NLPTEA的CGED数据集进行测试,取得了优于其他模型的结果。</abstract>
<identifier type="citekey">xie-etal-2020-ji</identifier>
<location>
<url>https://aclanthology.org/2020.ccl-1.71</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>761</start>
<end>770</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 基于数据增强和多任务特征学习的中文语法错误检测方法(Chinese Grammar Error Detection based on Data Enhancement and Multi-task Feature Learning)
%A Xie, Haihua
%A Chen, Zhiyou
%A Cheng, Jing
%A Lyu, Xiaoqing
%A Tang, Zhi
%Y Sun, Maosong
%Y Li, Sujian
%Y Zhang, Yue
%Y Liu, Yang
%S Proceedings of the 19th Chinese National Conference on Computational Linguistics
%D 2020
%8 October
%I Chinese Information Processing Society of China
%C Haikou, China
%G Chinese
%F xie-etal-2020-ji
%X 由于中文语法的复杂性,中文语法错误检测(CGED)的难度较大,而训练语料和相关研究的缺乏,使得CGED的效果还远达不到能够实用的程度。本文提出一种CGED模型,采用数据增强、预训练语言模型和基于语言学特征多任务学习的方式,弥补训练语料稀缺的不足。数据增强能够有效地扩充训练集,预训练语言模型蕴含丰富的语义信息有助于语法分析,基于语言学特征多任务学习对语言模型进行微调则可以使语言模型学习到跟语法错误检测相关的语言学特征。本文提出的方法在NLPTEA的CGED数据集进行测试,取得了优于其他模型的结果。
%U https://aclanthology.org/2020.ccl-1.71
%P 761-770
Markdown (Informal)
[基于数据增强和多任务特征学习的中文语法错误检测方法(Chinese Grammar Error Detection based on Data Enhancement and Multi-task Feature Learning)](https://aclanthology.org/2020.ccl-1.71) (Xie et al., CCL 2020)
ACL