@inproceedings{liang-etal-2022-multi,
title = "Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network",
author = "Liang, Bin and
Lou, Chenwei and
Li, Xiang and
Yang, Min and
Gui, Lin and
He, Yulan and
Pei, Wenjie and
Xu, Ruifeng",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.124",
doi = "10.18653/v1/2022.acl-long.124",
pages = "1767--1777",
abstract = "With the increasing popularity of posting multimodal messages online, many recent studies have been carried out utilizing both textual and visual information for multi-modal sarcasm detection. In this paper, we investigate multi-modal sarcasm detection from a novel perspective by constructing a cross-modal graph for each instance to explicitly draw the ironic relations between textual and visual modalities. Specifically, we first detect the objects paired with descriptions of the image modality, enabling the learning of important visual information. Then, the descriptions of the objects are served as a bridge to determine the importance of the association between the objects of image modality and the contextual words of text modality, so as to build a cross-modal graph for each multi-modal instance. Furthermore, we devise a cross-modal graph convolutional network to make sense of the incongruity relations between modalities for multi-modal sarcasm detection. Extensive experimental results and in-depth analysis show that our model achieves state-of-the-art performance in multi-modal sarcasm detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2022-multi">
<titleInfo>
<title>Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network</title>
</titleInfo>
<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">Chenwei</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Pei</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>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the increasing popularity of posting multimodal messages online, many recent studies have been carried out utilizing both textual and visual information for multi-modal sarcasm detection. In this paper, we investigate multi-modal sarcasm detection from a novel perspective by constructing a cross-modal graph for each instance to explicitly draw the ironic relations between textual and visual modalities. Specifically, we first detect the objects paired with descriptions of the image modality, enabling the learning of important visual information. Then, the descriptions of the objects are served as a bridge to determine the importance of the association between the objects of image modality and the contextual words of text modality, so as to build a cross-modal graph for each multi-modal instance. Furthermore, we devise a cross-modal graph convolutional network to make sense of the incongruity relations between modalities for multi-modal sarcasm detection. Extensive experimental results and in-depth analysis show that our model achieves state-of-the-art performance in multi-modal sarcasm detection.</abstract>
<identifier type="citekey">liang-etal-2022-multi</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.124</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.124</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1767</start>
<end>1777</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network
%A Liang, Bin
%A Lou, Chenwei
%A Li, Xiang
%A Yang, Min
%A Gui, Lin
%A He, Yulan
%A Pei, Wenjie
%A Xu, Ruifeng
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F liang-etal-2022-multi
%X With the increasing popularity of posting multimodal messages online, many recent studies have been carried out utilizing both textual and visual information for multi-modal sarcasm detection. In this paper, we investigate multi-modal sarcasm detection from a novel perspective by constructing a cross-modal graph for each instance to explicitly draw the ironic relations between textual and visual modalities. Specifically, we first detect the objects paired with descriptions of the image modality, enabling the learning of important visual information. Then, the descriptions of the objects are served as a bridge to determine the importance of the association between the objects of image modality and the contextual words of text modality, so as to build a cross-modal graph for each multi-modal instance. Furthermore, we devise a cross-modal graph convolutional network to make sense of the incongruity relations between modalities for multi-modal sarcasm detection. Extensive experimental results and in-depth analysis show that our model achieves state-of-the-art performance in multi-modal sarcasm detection.
%R 10.18653/v1/2022.acl-long.124
%U https://aclanthology.org/2022.acl-long.124
%U https://doi.org/10.18653/v1/2022.acl-long.124
%P 1767-1777
Markdown (Informal)
[Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network](https://aclanthology.org/2022.acl-long.124) (Liang et al., ACL 2022)
ACL
- Bin Liang, Chenwei Lou, Xiang Li, Min Yang, Lin Gui, Yulan He, Wenjie Pei, and Ruifeng Xu. 2022. Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1767–1777, Dublin, Ireland. Association for Computational Linguistics.