@inproceedings{congcong-etal-2023-ched,
title = "{CHED}: A Cross-Historical Dataset with a Logical Event Schema for Classical {C}hinese Event Detection",
author = "Congcong, Wei and
Zhenbing, Feng and
Shutan, Huang and
Wei, Li and
Yanqiu, Shao",
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-1.74/",
pages = "875--888",
language = "eng",
abstract = "{\textquotedblleft}Event detection (ED) is a crucial area of natural language processing that automates the extrac-tion of specific event types from large-scale text, and studying historical ED in classical Chinesetexts helps preserve and inherit historical and cultural heritage by extracting valuable informa-tion. However, classical Chinese language characteristics, such as ambiguous word classes andcomplex semantics, have posed challenges and led to a lack of datasets and limited research onevent schema construction. In addition, large-scale datasets in English and modern Chinese arenot directly applicable to historical ED in classical Chinese. To address these issues, we con-structed a logical event schema for classical Chinese historical texts and annotated the resultingdataset, which is called classical Chinese Historical Event Dataset (CHED). The main challengesin our work on classical Chinese historical ED are accurately identifying and classifying eventswithin cultural and linguistic contexts and addressing ambiguity resulting from multiple mean-ings of words in historical texts. Therefore, we have developed a set of annotation guidelinesand provided annotators with an objective reference translation. The average Kappa coefficientafter multiple cross-validation is 68.49{\%}, indicating high quality and consistency. We conductedvarious tasks and comparative experiments on established baseline models for historical ED inclassical Chinese. The results showed that BERT+CRF had the best performance on sequencelabeling task, with an f1-score of 76.10{\%}, indicating potential for further improvement. 1Introduction{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="congcong-etal-2023-ched">
<titleInfo>
<title>CHED: A Cross-Historical Dataset with a Logical Event Schema for Classical Chinese Event Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Congcong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Zhenbing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huang</namePart>
<namePart type="family">Shutan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shao</namePart>
<namePart type="family">Yanqiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</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>“Event detection (ED) is a crucial area of natural language processing that automates the extrac-tion of specific event types from large-scale text, and studying historical ED in classical Chinesetexts helps preserve and inherit historical and cultural heritage by extracting valuable informa-tion. However, classical Chinese language characteristics, such as ambiguous word classes andcomplex semantics, have posed challenges and led to a lack of datasets and limited research onevent schema construction. In addition, large-scale datasets in English and modern Chinese arenot directly applicable to historical ED in classical Chinese. To address these issues, we con-structed a logical event schema for classical Chinese historical texts and annotated the resultingdataset, which is called classical Chinese Historical Event Dataset (CHED). The main challengesin our work on classical Chinese historical ED are accurately identifying and classifying eventswithin cultural and linguistic contexts and addressing ambiguity resulting from multiple mean-ings of words in historical texts. Therefore, we have developed a set of annotation guidelinesand provided annotators with an objective reference translation. The average Kappa coefficientafter multiple cross-validation is 68.49%, indicating high quality and consistency. We conductedvarious tasks and comparative experiments on established baseline models for historical ED inclassical Chinese. The results showed that BERT+CRF had the best performance on sequencelabeling task, with an f1-score of 76.10%, indicating potential for further improvement. 1Introduction”</abstract>
<identifier type="citekey">congcong-etal-2023-ched</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-1.74/</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>875</start>
<end>888</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CHED: A Cross-Historical Dataset with a Logical Event Schema for Classical Chinese Event Detection
%A Congcong, Wei
%A Zhenbing, Feng
%A Shutan, Huang
%A Wei, Li
%A Yanqiu, Shao
%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 eng
%F congcong-etal-2023-ched
%X “Event detection (ED) is a crucial area of natural language processing that automates the extrac-tion of specific event types from large-scale text, and studying historical ED in classical Chinesetexts helps preserve and inherit historical and cultural heritage by extracting valuable informa-tion. However, classical Chinese language characteristics, such as ambiguous word classes andcomplex semantics, have posed challenges and led to a lack of datasets and limited research onevent schema construction. In addition, large-scale datasets in English and modern Chinese arenot directly applicable to historical ED in classical Chinese. To address these issues, we con-structed a logical event schema for classical Chinese historical texts and annotated the resultingdataset, which is called classical Chinese Historical Event Dataset (CHED). The main challengesin our work on classical Chinese historical ED are accurately identifying and classifying eventswithin cultural and linguistic contexts and addressing ambiguity resulting from multiple mean-ings of words in historical texts. Therefore, we have developed a set of annotation guidelinesand provided annotators with an objective reference translation. The average Kappa coefficientafter multiple cross-validation is 68.49%, indicating high quality and consistency. We conductedvarious tasks and comparative experiments on established baseline models for historical ED inclassical Chinese. The results showed that BERT+CRF had the best performance on sequencelabeling task, with an f1-score of 76.10%, indicating potential for further improvement. 1Introduction”
%U https://aclanthology.org/2023.ccl-1.74/
%P 875-888
Markdown (Informal)
[CHED: A Cross-Historical Dataset with a Logical Event Schema for Classical Chinese Event Detection](https://aclanthology.org/2023.ccl-1.74/) (Congcong et al., CCL 2023)
ACL