@inproceedings{xu-etal-2020-reasoning,
title = "Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association",
author = "Xu, Nan and
Zeng, Zhixiong and
Mao, Wenji",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.349",
doi = "10.18653/v1/2020.acl-main.349",
pages = "3777--3786",
abstract = "Sarcasm is a sophisticated linguistic phenomenon to express the opposite of what one really means. With the rapid growth of social media, multimodal sarcastic tweets are widely posted on various social platforms. In multimodal context, sarcasm is no longer a pure linguistic phenomenon, and due to the nature of social media short text, the opposite is more often manifested via cross-modality expressions. Thus traditional text-based methods are insufficient to detect multimodal sarcasm. To reason with multimodal sarcastic tweets, in this paper, we propose a novel method for modeling cross-modality contrast in the associated context. Our method models both cross-modality contrast and semantic association by constructing the Decomposition and Relation Network (namely D{\&}R Net). The decomposition network represents the commonality and discrepancy between image and text, and the relation network models the semantic association in cross-modality context. Experimental results on a public dataset demonstrate the effectiveness of our model in multimodal sarcasm detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2020-reasoning">
<titleInfo>
<title>Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhixiong</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenji</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sarcasm is a sophisticated linguistic phenomenon to express the opposite of what one really means. With the rapid growth of social media, multimodal sarcastic tweets are widely posted on various social platforms. In multimodal context, sarcasm is no longer a pure linguistic phenomenon, and due to the nature of social media short text, the opposite is more often manifested via cross-modality expressions. Thus traditional text-based methods are insufficient to detect multimodal sarcasm. To reason with multimodal sarcastic tweets, in this paper, we propose a novel method for modeling cross-modality contrast in the associated context. Our method models both cross-modality contrast and semantic association by constructing the Decomposition and Relation Network (namely D&R Net). The decomposition network represents the commonality and discrepancy between image and text, and the relation network models the semantic association in cross-modality context. Experimental results on a public dataset demonstrate the effectiveness of our model in multimodal sarcasm detection.</abstract>
<identifier type="citekey">xu-etal-2020-reasoning</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.349</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.349</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>3777</start>
<end>3786</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association
%A Xu, Nan
%A Zeng, Zhixiong
%A Mao, Wenji
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F xu-etal-2020-reasoning
%X Sarcasm is a sophisticated linguistic phenomenon to express the opposite of what one really means. With the rapid growth of social media, multimodal sarcastic tweets are widely posted on various social platforms. In multimodal context, sarcasm is no longer a pure linguistic phenomenon, and due to the nature of social media short text, the opposite is more often manifested via cross-modality expressions. Thus traditional text-based methods are insufficient to detect multimodal sarcasm. To reason with multimodal sarcastic tweets, in this paper, we propose a novel method for modeling cross-modality contrast in the associated context. Our method models both cross-modality contrast and semantic association by constructing the Decomposition and Relation Network (namely D&R Net). The decomposition network represents the commonality and discrepancy between image and text, and the relation network models the semantic association in cross-modality context. Experimental results on a public dataset demonstrate the effectiveness of our model in multimodal sarcasm detection.
%R 10.18653/v1/2020.acl-main.349
%U https://aclanthology.org/2020.acl-main.349
%U https://doi.org/10.18653/v1/2020.acl-main.349
%P 3777-3786
Markdown (Informal)
[Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association](https://aclanthology.org/2020.acl-main.349) (Xu et al., ACL 2020)
ACL