@inproceedings{qin-etal-2023-mmsd2,
title = "{MMSD}2.0: Towards a Reliable Multi-modal Sarcasm Detection System",
author = "Qin, Libo and
Huang, Shijue and
Chen, Qiguang and
Cai, Chenran and
Zhang, Yudi and
Liang, Bin and
Che, Wanxiang and
Xu, Ruifeng",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.689/",
doi = "10.18653/v1/2023.findings-acl.689",
pages = "10834--10845",
abstract = "Multi-modal sarcasm detection has attracted much recent attention. Nevertheless, the existing benchmark (MMSD) has some shortcomings that hinder the development of reliable multi-modal sarcasm detection system: (1) There are some spurious cues in MMSD, leading to the model bias learning; (2) The negative samples in MMSD are not always reasonable. To solve the aforementioned issues, we introduce MMSD2.0, a correction dataset that fixes the shortcomings of MMSD, by removing the spurious cues and re-annotating the unreasonable samples. Meanwhile, we present a novel framework called multi-view CLIP that is capable of leveraging multi-grained cues from multiple perspectives (i.e., text, image, and text-image interaction view) for multi-modal sarcasm detection. Extensive experiments show that MMSD2.0 is a valuable benchmark for building reliable multi-modal sarcasm detection systems and multi-view CLIP can significantly outperform the previous best baselines."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-etal-2023-mmsd2">
<titleInfo>
<title>MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Libo</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijue</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiguang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenran</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</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>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-modal sarcasm detection has attracted much recent attention. Nevertheless, the existing benchmark (MMSD) has some shortcomings that hinder the development of reliable multi-modal sarcasm detection system: (1) There are some spurious cues in MMSD, leading to the model bias learning; (2) The negative samples in MMSD are not always reasonable. To solve the aforementioned issues, we introduce MMSD2.0, a correction dataset that fixes the shortcomings of MMSD, by removing the spurious cues and re-annotating the unreasonable samples. Meanwhile, we present a novel framework called multi-view CLIP that is capable of leveraging multi-grained cues from multiple perspectives (i.e., text, image, and text-image interaction view) for multi-modal sarcasm detection. Extensive experiments show that MMSD2.0 is a valuable benchmark for building reliable multi-modal sarcasm detection systems and multi-view CLIP can significantly outperform the previous best baselines.</abstract>
<identifier type="citekey">qin-etal-2023-mmsd2</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.689</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.689/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>10834</start>
<end>10845</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System
%A Qin, Libo
%A Huang, Shijue
%A Chen, Qiguang
%A Cai, Chenran
%A Zhang, Yudi
%A Liang, Bin
%A Che, Wanxiang
%A Xu, Ruifeng
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F qin-etal-2023-mmsd2
%X Multi-modal sarcasm detection has attracted much recent attention. Nevertheless, the existing benchmark (MMSD) has some shortcomings that hinder the development of reliable multi-modal sarcasm detection system: (1) There are some spurious cues in MMSD, leading to the model bias learning; (2) The negative samples in MMSD are not always reasonable. To solve the aforementioned issues, we introduce MMSD2.0, a correction dataset that fixes the shortcomings of MMSD, by removing the spurious cues and re-annotating the unreasonable samples. Meanwhile, we present a novel framework called multi-view CLIP that is capable of leveraging multi-grained cues from multiple perspectives (i.e., text, image, and text-image interaction view) for multi-modal sarcasm detection. Extensive experiments show that MMSD2.0 is a valuable benchmark for building reliable multi-modal sarcasm detection systems and multi-view CLIP can significantly outperform the previous best baselines.
%R 10.18653/v1/2023.findings-acl.689
%U https://aclanthology.org/2023.findings-acl.689/
%U https://doi.org/10.18653/v1/2023.findings-acl.689
%P 10834-10845
Markdown (Informal)
[MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System](https://aclanthology.org/2023.findings-acl.689/) (Qin et al., Findings 2023)
ACL
- Libo Qin, Shijue Huang, Qiguang Chen, Chenran Cai, Yudi Zhang, Bin Liang, Wanxiang Che, and Ruifeng Xu. 2023. MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System. In Findings of the Association for Computational Linguistics: ACL 2023, pages 10834–10845, Toronto, Canada. Association for Computational Linguistics.