@inproceedings{gong-etal-2020-design,
title = "The Design and Construction of a {C}hinese Sarcasm Dataset",
author = "Gong, Xiaochang and
Zhao, Qin and
Zhang, Jun and
Mao, Ruibin and
Xu, Ruifeng",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.619/",
pages = "5034--5039",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "As a typical multi-layered semi-conscious language phenomenon, sarcasm is widely existed in social media text for enhancing the emotion expression. Thus, the detection and processing of sarcasm is important to social media analysis. However, most existing sarcasm dataset are in English and there is still a lack of authoritative Chinese sarcasm dataset. In this paper, we presents the design and construction of a largest high-quality Chinese sarcasm dataset, which contains 2,486 manual annotated sarcastic texts and 89,296 non-sarcastic texts. Furthermore, a balanced dataset through elaborately sampling the same amount non-sarcastic texts for training sarcasm classifier. Using the dataset as the benchmark, some sarcasm classification methods are evaluated."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gong-etal-2020-design">
<titleInfo>
<title>The Design and Construction of a Chinese Sarcasm Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaochang</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruibin</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>As a typical multi-layered semi-conscious language phenomenon, sarcasm is widely existed in social media text for enhancing the emotion expression. Thus, the detection and processing of sarcasm is important to social media analysis. However, most existing sarcasm dataset are in English and there is still a lack of authoritative Chinese sarcasm dataset. In this paper, we presents the design and construction of a largest high-quality Chinese sarcasm dataset, which contains 2,486 manual annotated sarcastic texts and 89,296 non-sarcastic texts. Furthermore, a balanced dataset through elaborately sampling the same amount non-sarcastic texts for training sarcasm classifier. Using the dataset as the benchmark, some sarcasm classification methods are evaluated.</abstract>
<identifier type="citekey">gong-etal-2020-design</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.619/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5034</start>
<end>5039</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Design and Construction of a Chinese Sarcasm Dataset
%A Gong, Xiaochang
%A Zhao, Qin
%A Zhang, Jun
%A Mao, Ruibin
%A Xu, Ruifeng
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F gong-etal-2020-design
%X As a typical multi-layered semi-conscious language phenomenon, sarcasm is widely existed in social media text for enhancing the emotion expression. Thus, the detection and processing of sarcasm is important to social media analysis. However, most existing sarcasm dataset are in English and there is still a lack of authoritative Chinese sarcasm dataset. In this paper, we presents the design and construction of a largest high-quality Chinese sarcasm dataset, which contains 2,486 manual annotated sarcastic texts and 89,296 non-sarcastic texts. Furthermore, a balanced dataset through elaborately sampling the same amount non-sarcastic texts for training sarcasm classifier. Using the dataset as the benchmark, some sarcasm classification methods are evaluated.
%U https://aclanthology.org/2020.lrec-1.619/
%P 5034-5039
Markdown (Informal)
[The Design and Construction of a Chinese Sarcasm Dataset](https://aclanthology.org/2020.lrec-1.619/) (Gong et al., LREC 2020)
ACL
- Xiaochang Gong, Qin Zhao, Jun Zhang, Ruibin Mao, and Ruifeng Xu. 2020. The Design and Construction of a Chinese Sarcasm Dataset. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5034–5039, Marseille, France. European Language Resources Association.