@inproceedings{wang-etal-2023-gu,
title = "古汉语通假字资源库的构建及应用研究(The Construction and Application of an {A}ncient {C}hinese Language Resource on Tongjiazi)",
author = "Wang, Zhaoji and
Zhang, Shirui and
Zhang, Xuetao and
Hu, Renfen",
editor = "Sun, Maosong and
Qin, Bing and
Qiu, Xipeng and
Jiang, Jing and
Han, Xianpei",
booktitle = "Proceedings of the 22nd Chinese National Conference on Computational Linguistics",
month = aug,
year = "2023",
address = "Harbin, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2023.ccl-1.47/",
pages = "535--546",
language = "zho",
abstract = "{\textquotedblleft}古籍文本中的文字通假现象较为常见,这不仅为人理解文意造成了困难,也是古汉语信息处理面临的一项重要挑战。为了服务于通假字的人工判别和机器处理,本文构建并开源了一个多维度的通假字资源库,包括语料库、知识库和评测数据集三个子库。其中,语料库收录11000余条包含通假现象详细标注的语料;知识库以汉字为节点,通假和形声关系为边,从字音、字形、字义多个角度对通假字与正字的属性进行加工,共包含4185个字节点和8350对关联信息;评测数据集面向古汉语信息处理需求,支持通假字检测和正字识别两个子任务的评测,收录评测数据19678条。在此基础上,本文搭建了通假字自动识别的系列基线模型,并结合试验结果分析了影响通假字自动识别的因素与改进方法。进一步地,本文探讨了该资源库在古籍整理、人文研究和文言文教学中的应用。{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-gu">
<titleInfo>
<title>古汉语通假字资源库的构建及应用研究(The Construction and Application of an Ancient Chinese Language Resource on Tongjiazi)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhaoji</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shirui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuetao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renfen</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">zho</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd 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">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Harbin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“古籍文本中的文字通假现象较为常见,这不仅为人理解文意造成了困难,也是古汉语信息处理面临的一项重要挑战。为了服务于通假字的人工判别和机器处理,本文构建并开源了一个多维度的通假字资源库,包括语料库、知识库和评测数据集三个子库。其中,语料库收录11000余条包含通假现象详细标注的语料;知识库以汉字为节点,通假和形声关系为边,从字音、字形、字义多个角度对通假字与正字的属性进行加工,共包含4185个字节点和8350对关联信息;评测数据集面向古汉语信息处理需求,支持通假字检测和正字识别两个子任务的评测,收录评测数据19678条。在此基础上,本文搭建了通假字自动识别的系列基线模型,并结合试验结果分析了影响通假字自动识别的因素与改进方法。进一步地,本文探讨了该资源库在古籍整理、人文研究和文言文教学中的应用。”</abstract>
<identifier type="citekey">wang-etal-2023-gu</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-1.47/</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>535</start>
<end>546</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 古汉语通假字资源库的构建及应用研究(The Construction and Application of an Ancient Chinese Language Resource on Tongjiazi)
%A Wang, Zhaoji
%A Zhang, Shirui
%A Zhang, Xuetao
%A Hu, Renfen
%Y Sun, Maosong
%Y Qin, Bing
%Y Qiu, Xipeng
%Y Jiang, Jing
%Y Han, Xianpei
%S Proceedings of the 22nd Chinese National Conference on Computational Linguistics
%D 2023
%8 August
%I Chinese Information Processing Society of China
%C Harbin, China
%G zho
%F wang-etal-2023-gu
%X “古籍文本中的文字通假现象较为常见,这不仅为人理解文意造成了困难,也是古汉语信息处理面临的一项重要挑战。为了服务于通假字的人工判别和机器处理,本文构建并开源了一个多维度的通假字资源库,包括语料库、知识库和评测数据集三个子库。其中,语料库收录11000余条包含通假现象详细标注的语料;知识库以汉字为节点,通假和形声关系为边,从字音、字形、字义多个角度对通假字与正字的属性进行加工,共包含4185个字节点和8350对关联信息;评测数据集面向古汉语信息处理需求,支持通假字检测和正字识别两个子任务的评测,收录评测数据19678条。在此基础上,本文搭建了通假字自动识别的系列基线模型,并结合试验结果分析了影响通假字自动识别的因素与改进方法。进一步地,本文探讨了该资源库在古籍整理、人文研究和文言文教学中的应用。”
%U https://aclanthology.org/2023.ccl-1.47/
%P 535-546
Markdown (Informal)
[古汉语通假字资源库的构建及应用研究(The Construction and Application of an Ancient Chinese Language Resource on Tongjiazi)](https://aclanthology.org/2023.ccl-1.47/) (Wang et al., CCL 2023)
ACL