@inproceedings{li-etal-2025-ambiguity,
title = "Ambiguity-aware Multi-level Incongruity Fusion Network for Multi-Modal Sarcasm Detection",
author = "Li, Kuntao and
Chen, Yifan and
Wu, Qiaofeng and
Mai, Weixing and
Li, Fenghuan and
Xue, Yun",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.26/",
pages = "380--391",
abstract = "Multi-modal sarcasm detection aims to identify whether a given image-text pair is sarcastic. The pivotal factor of the task lies in accurately capturing incongruities from different modalities. Although existing studies have achieved impressive success, they primarily committed to fusing the textual and visual information to establish cross-modal correlations, overlooking the significance of original unimodal incongruity information at the text-level and image-level. Furthermore, the utilized fusion strategies of cross-modal information neglected the effect of inherent ambiguity within text and image modalities on multimodal fusion. To overcome these limitations, we propose a novel Ambiguity-aware Multi-level Incongruity Fusion Network (AMIF) for multi-modal sarcasm detection. Our method involves a multi-level incongruity learning module to capture the incongruity information simultaneously at the text-level, image-level and cross-modal-level. Additionally, an ambiguity-based fusion module is developed to dynamically learn reasonable weights and interpretably aggregate incongruity features from different levels. Comprehensive experiments conducted on a publicly available dataset demonstrate the superiority of our proposed model over state-of-the-art methods."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-ambiguity">
<titleInfo>
<title>Ambiguity-aware Multi-level Incongruity Fusion Network for Multi-Modal Sarcasm Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kuntao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiaofeng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weixing</namePart>
<namePart type="family">Mai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fenghuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-modal sarcasm detection aims to identify whether a given image-text pair is sarcastic. The pivotal factor of the task lies in accurately capturing incongruities from different modalities. Although existing studies have achieved impressive success, they primarily committed to fusing the textual and visual information to establish cross-modal correlations, overlooking the significance of original unimodal incongruity information at the text-level and image-level. Furthermore, the utilized fusion strategies of cross-modal information neglected the effect of inherent ambiguity within text and image modalities on multimodal fusion. To overcome these limitations, we propose a novel Ambiguity-aware Multi-level Incongruity Fusion Network (AMIF) for multi-modal sarcasm detection. Our method involves a multi-level incongruity learning module to capture the incongruity information simultaneously at the text-level, image-level and cross-modal-level. Additionally, an ambiguity-based fusion module is developed to dynamically learn reasonable weights and interpretably aggregate incongruity features from different levels. Comprehensive experiments conducted on a publicly available dataset demonstrate the superiority of our proposed model over state-of-the-art methods.</abstract>
<identifier type="citekey">li-etal-2025-ambiguity</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.26/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>380</start>
<end>391</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ambiguity-aware Multi-level Incongruity Fusion Network for Multi-Modal Sarcasm Detection
%A Li, Kuntao
%A Chen, Yifan
%A Wu, Qiaofeng
%A Mai, Weixing
%A Li, Fenghuan
%A Xue, Yun
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F li-etal-2025-ambiguity
%X Multi-modal sarcasm detection aims to identify whether a given image-text pair is sarcastic. The pivotal factor of the task lies in accurately capturing incongruities from different modalities. Although existing studies have achieved impressive success, they primarily committed to fusing the textual and visual information to establish cross-modal correlations, overlooking the significance of original unimodal incongruity information at the text-level and image-level. Furthermore, the utilized fusion strategies of cross-modal information neglected the effect of inherent ambiguity within text and image modalities on multimodal fusion. To overcome these limitations, we propose a novel Ambiguity-aware Multi-level Incongruity Fusion Network (AMIF) for multi-modal sarcasm detection. Our method involves a multi-level incongruity learning module to capture the incongruity information simultaneously at the text-level, image-level and cross-modal-level. Additionally, an ambiguity-based fusion module is developed to dynamically learn reasonable weights and interpretably aggregate incongruity features from different levels. Comprehensive experiments conducted on a publicly available dataset demonstrate the superiority of our proposed model over state-of-the-art methods.
%U https://aclanthology.org/2025.coling-main.26/
%P 380-391
Markdown (Informal)
[Ambiguity-aware Multi-level Incongruity Fusion Network for Multi-Modal Sarcasm Detection](https://aclanthology.org/2025.coling-main.26/) (Li et al., COLING 2025)
ACL