@inproceedings{li-etal-2022-clgc,
title = "{CLGC}: A Corpus for {C}hinese Literary Grace Evaluation",
author = "Li, Yi and
Yu, Dong and
Liu, Pengyuan",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.594",
pages = "5548--5556",
abstract = "In this paper, we construct a Chinese literary grace corpus, CLGC, with 10,000 texts and more than 1.85 million tokens. Multi-level annotations are provided for each text in our corpus, including literary grace level, sentence category, and figure-of-speech type. Based on the corpus, we dig deep into the correlation between fine-grained features (semantic information, part-of-speech and figure-of-speech, etc.) and literary grace level. We also propose a new Literary Grace Evaluation (LGE) task, which aims at making a comprehensive assessment of the literary grace level according to the text. In the end, we build some classification models with machine learning algorithms (such as SVM, TextCNN) to prove the effectiveness of our features and corpus for LGE. The results of our preliminary classification experiments have achieved 79.71{\%} on the weighted average F1-score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-clgc">
<titleInfo>
<title>CLGC: A Corpus for Chinese Literary Grace Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we construct a Chinese literary grace corpus, CLGC, with 10,000 texts and more than 1.85 million tokens. Multi-level annotations are provided for each text in our corpus, including literary grace level, sentence category, and figure-of-speech type. Based on the corpus, we dig deep into the correlation between fine-grained features (semantic information, part-of-speech and figure-of-speech, etc.) and literary grace level. We also propose a new Literary Grace Evaluation (LGE) task, which aims at making a comprehensive assessment of the literary grace level according to the text. In the end, we build some classification models with machine learning algorithms (such as SVM, TextCNN) to prove the effectiveness of our features and corpus for LGE. The results of our preliminary classification experiments have achieved 79.71% on the weighted average F1-score.</abstract>
<identifier type="citekey">li-etal-2022-clgc</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.594</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5548</start>
<end>5556</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLGC: A Corpus for Chinese Literary Grace Evaluation
%A Li, Yi
%A Yu, Dong
%A Liu, Pengyuan
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F li-etal-2022-clgc
%X In this paper, we construct a Chinese literary grace corpus, CLGC, with 10,000 texts and more than 1.85 million tokens. Multi-level annotations are provided for each text in our corpus, including literary grace level, sentence category, and figure-of-speech type. Based on the corpus, we dig deep into the correlation between fine-grained features (semantic information, part-of-speech and figure-of-speech, etc.) and literary grace level. We also propose a new Literary Grace Evaluation (LGE) task, which aims at making a comprehensive assessment of the literary grace level according to the text. In the end, we build some classification models with machine learning algorithms (such as SVM, TextCNN) to prove the effectiveness of our features and corpus for LGE. The results of our preliminary classification experiments have achieved 79.71% on the weighted average F1-score.
%U https://aclanthology.org/2022.lrec-1.594
%P 5548-5556
Markdown (Informal)
[CLGC: A Corpus for Chinese Literary Grace Evaluation](https://aclanthology.org/2022.lrec-1.594) (Li et al., LREC 2022)
ACL