@inproceedings{guo-etal-2024-much-multimodal,
title = "{MUCH}: A Multimodal Corpus Construction for Conversational Humor Recognition Based on {C}hinese Sitcom",
author = "Guo, Hongyu and
Shang, Wenbo and
Zhang, Xueyao and
Li, Binyang",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1021",
pages = "11692--11698",
abstract = "Conversational humor is the key to capturing dialogue semantics and dialogue comprehension, which is usually generated in multiple modalities, such as linguistic rhetoric (textual modality), exaggerated facial expressions or movements (visual modality), and quirky intonation (acoustic modality). However, existing multimodal corpora for conversation humor are coarse-grained, and the modality is insufficient to support the conversational humor recognition task. This paper designed an annotation scheme for multimodal humor datasets, and constructed a corpus based on a Chinese sitcom for conversational humor recognition, named MUCH. The MUCH corpus consists of 34,804 utterances in total, and 7,079 of them are humorous. We employed both unimodal and multimodal methods to test our MUCH corpus. Experimental results showed that the multimodal approach could achieve 75.94{\%} in terms of F1-score and surpassed the performance of most unimodal methods, which demonstrated that the MUCH corpus was effective for multimodal humor recognition tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2024-much-multimodal">
<titleInfo>
<title>MUCH: A Multimodal Corpus Construction for Conversational Humor Recognition Based on Chinese Sitcom</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbo</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueyao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conversational humor is the key to capturing dialogue semantics and dialogue comprehension, which is usually generated in multiple modalities, such as linguistic rhetoric (textual modality), exaggerated facial expressions or movements (visual modality), and quirky intonation (acoustic modality). However, existing multimodal corpora for conversation humor are coarse-grained, and the modality is insufficient to support the conversational humor recognition task. This paper designed an annotation scheme for multimodal humor datasets, and constructed a corpus based on a Chinese sitcom for conversational humor recognition, named MUCH. The MUCH corpus consists of 34,804 utterances in total, and 7,079 of them are humorous. We employed both unimodal and multimodal methods to test our MUCH corpus. Experimental results showed that the multimodal approach could achieve 75.94% in terms of F1-score and surpassed the performance of most unimodal methods, which demonstrated that the MUCH corpus was effective for multimodal humor recognition tasks.</abstract>
<identifier type="citekey">guo-etal-2024-much-multimodal</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1021</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11692</start>
<end>11698</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MUCH: A Multimodal Corpus Construction for Conversational Humor Recognition Based on Chinese Sitcom
%A Guo, Hongyu
%A Shang, Wenbo
%A Zhang, Xueyao
%A Li, Binyang
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F guo-etal-2024-much-multimodal
%X Conversational humor is the key to capturing dialogue semantics and dialogue comprehension, which is usually generated in multiple modalities, such as linguistic rhetoric (textual modality), exaggerated facial expressions or movements (visual modality), and quirky intonation (acoustic modality). However, existing multimodal corpora for conversation humor are coarse-grained, and the modality is insufficient to support the conversational humor recognition task. This paper designed an annotation scheme for multimodal humor datasets, and constructed a corpus based on a Chinese sitcom for conversational humor recognition, named MUCH. The MUCH corpus consists of 34,804 utterances in total, and 7,079 of them are humorous. We employed both unimodal and multimodal methods to test our MUCH corpus. Experimental results showed that the multimodal approach could achieve 75.94% in terms of F1-score and surpassed the performance of most unimodal methods, which demonstrated that the MUCH corpus was effective for multimodal humor recognition tasks.
%U https://aclanthology.org/2024.lrec-main.1021
%P 11692-11698
Markdown (Informal)
[MUCH: A Multimodal Corpus Construction for Conversational Humor Recognition Based on Chinese Sitcom](https://aclanthology.org/2024.lrec-main.1021) (Guo et al., LREC-COLING 2024)
ACL