@inproceedings{liu-etal-2022-towards-multi-modal,
title = "Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement",
author = "Liu, Hui and
Wang, Wenya and
Li, Haoliang",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.333",
doi = "10.18653/v1/2022.emnlp-main.333",
pages = "4995--5006",
abstract = "Sarcasm is a linguistic phenomenon indicating a discrepancy between literal meanings and implied intentions. Due to its sophisticated nature, it is usually difficult to be detected from the text itself. As a result, multi-modal sarcasm detection has received more and more attention in both academia and industries. However, most existing techniques only modeled the atomic-level inconsistencies between the text input and its accompanying image, ignoring more complex compositions for both modalities. Moreover, they neglected the rich information contained in external knowledge, e.g., image captions. In this paper, we propose a novel hierarchical framework for sarcasm detection by exploring both the atomic-level congruity based on multi-head cross attentions and the composition-level congruity based on graph neural networks, where a post with low congruity can be identified as sarcasm. In addition, we exploit the effect of various knowledge resources for sarcasm detection. Evaluation results on a public multi-modal sarcasm detection dataset based on Twitter demonstrate the superiority of our proposed model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-towards-multi-modal">
<titleInfo>
<title>Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenya</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoliang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sarcasm is a linguistic phenomenon indicating a discrepancy between literal meanings and implied intentions. Due to its sophisticated nature, it is usually difficult to be detected from the text itself. As a result, multi-modal sarcasm detection has received more and more attention in both academia and industries. However, most existing techniques only modeled the atomic-level inconsistencies between the text input and its accompanying image, ignoring more complex compositions for both modalities. Moreover, they neglected the rich information contained in external knowledge, e.g., image captions. In this paper, we propose a novel hierarchical framework for sarcasm detection by exploring both the atomic-level congruity based on multi-head cross attentions and the composition-level congruity based on graph neural networks, where a post with low congruity can be identified as sarcasm. In addition, we exploit the effect of various knowledge resources for sarcasm detection. Evaluation results on a public multi-modal sarcasm detection dataset based on Twitter demonstrate the superiority of our proposed model.</abstract>
<identifier type="citekey">liu-etal-2022-towards-multi-modal</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.333</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.333</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4995</start>
<end>5006</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement
%A Liu, Hui
%A Wang, Wenya
%A Li, Haoliang
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F liu-etal-2022-towards-multi-modal
%X Sarcasm is a linguistic phenomenon indicating a discrepancy between literal meanings and implied intentions. Due to its sophisticated nature, it is usually difficult to be detected from the text itself. As a result, multi-modal sarcasm detection has received more and more attention in both academia and industries. However, most existing techniques only modeled the atomic-level inconsistencies between the text input and its accompanying image, ignoring more complex compositions for both modalities. Moreover, they neglected the rich information contained in external knowledge, e.g., image captions. In this paper, we propose a novel hierarchical framework for sarcasm detection by exploring both the atomic-level congruity based on multi-head cross attentions and the composition-level congruity based on graph neural networks, where a post with low congruity can be identified as sarcasm. In addition, we exploit the effect of various knowledge resources for sarcasm detection. Evaluation results on a public multi-modal sarcasm detection dataset based on Twitter demonstrate the superiority of our proposed model.
%R 10.18653/v1/2022.emnlp-main.333
%U https://aclanthology.org/2022.emnlp-main.333
%U https://doi.org/10.18653/v1/2022.emnlp-main.333
%P 4995-5006
Markdown (Informal)
[Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement](https://aclanthology.org/2022.emnlp-main.333) (Liu et al., EMNLP 2022)
ACL