@inproceedings{tseng-etal-2020-development,
title = "Development and Validation of a Corpus for Machine Humor Comprehension",
author = "Tseng, Yuen-Hsien and
Wu, Wun-Syuan and
Chang, Chia-Yueh and
Chen, Hsueh-Chih and
Hsu, Wei-Lun",
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-1.168",
pages = "1346--1352",
abstract = "This work developed a Chinese humor corpus containing 3,365 jokes collected from over 40 sources. Each joke was labeled with five levels of funniness, eight skill sets of humor, and six dimensions of intent by only one annotator. To validate the manual labels, we trained SVM (Support Vector Machine) and BERT (Bidirectional Encoder Representations from Transformers) with half of the corpus (labeled by one annotator) to predict the skill and intent labels of the other half (labeled by the other annotator). Based on two assumptions that a valid manually labeled corpus should follow, our results showed the validity for the skill and intent labels. As to the funniness label, the validation results showed that the correlation between the corpus label and user feedback rating is marginal, which implies that the funniness level is a harder annotation problem to be solved. The contribution of this work is two folds: 1) a Chinese humor corpus is developed with labels of humor skills, intents, and funniness, which allows machines to learn more intricate humor framing, effect, and amusing level to predict and respond in proper context (\url{https://github.com/SamTseng/Chinese_Humor_MultiLabeled}). 2) An approach to verify whether a minimum human labeled corpus is valid or not, which facilitates the validation of low-resource corpora.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tseng-etal-2020-development">
<titleInfo>
<title>Development and Validation of a Corpus for Machine Humor Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuen-Hsien</namePart>
<namePart type="family">Tseng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wun-Syuan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Yueh</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsueh-Chih</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Lun</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">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>This work developed a Chinese humor corpus containing 3,365 jokes collected from over 40 sources. Each joke was labeled with five levels of funniness, eight skill sets of humor, and six dimensions of intent by only one annotator. To validate the manual labels, we trained SVM (Support Vector Machine) and BERT (Bidirectional Encoder Representations from Transformers) with half of the corpus (labeled by one annotator) to predict the skill and intent labels of the other half (labeled by the other annotator). Based on two assumptions that a valid manually labeled corpus should follow, our results showed the validity for the skill and intent labels. As to the funniness label, the validation results showed that the correlation between the corpus label and user feedback rating is marginal, which implies that the funniness level is a harder annotation problem to be solved. The contribution of this work is two folds: 1) a Chinese humor corpus is developed with labels of humor skills, intents, and funniness, which allows machines to learn more intricate humor framing, effect, and amusing level to predict and respond in proper context (https://github.com/SamTseng/Chinese_Humor_MultiLabeled). 2) An approach to verify whether a minimum human labeled corpus is valid or not, which facilitates the validation of low-resource corpora.</abstract>
<identifier type="citekey">tseng-etal-2020-development</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.168</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1346</start>
<end>1352</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development and Validation of a Corpus for Machine Humor Comprehension
%A Tseng, Yuen-Hsien
%A Wu, Wun-Syuan
%A Chang, Chia-Yueh
%A Chen, Hsueh-Chih
%A Hsu, Wei-Lun
%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 English
%F tseng-etal-2020-development
%X This work developed a Chinese humor corpus containing 3,365 jokes collected from over 40 sources. Each joke was labeled with five levels of funniness, eight skill sets of humor, and six dimensions of intent by only one annotator. To validate the manual labels, we trained SVM (Support Vector Machine) and BERT (Bidirectional Encoder Representations from Transformers) with half of the corpus (labeled by one annotator) to predict the skill and intent labels of the other half (labeled by the other annotator). Based on two assumptions that a valid manually labeled corpus should follow, our results showed the validity for the skill and intent labels. As to the funniness label, the validation results showed that the correlation between the corpus label and user feedback rating is marginal, which implies that the funniness level is a harder annotation problem to be solved. The contribution of this work is two folds: 1) a Chinese humor corpus is developed with labels of humor skills, intents, and funniness, which allows machines to learn more intricate humor framing, effect, and amusing level to predict and respond in proper context (https://github.com/SamTseng/Chinese_Humor_MultiLabeled). 2) An approach to verify whether a minimum human labeled corpus is valid or not, which facilitates the validation of low-resource corpora.
%U https://aclanthology.org/2020.lrec-1.168
%P 1346-1352
Markdown (Informal)
[Development and Validation of a Corpus for Machine Humor Comprehension](https://aclanthology.org/2020.lrec-1.168) (Tseng et al., LREC 2020)
ACL