@inproceedings{yang-etal-2024-uncertainty,
title = "Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection",
author = "Yang, Chuanpeng and
Zhu, Fuqing and
Liu, Yaxin and
Han, Jizhong and
Hu, Songlin",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1475",
pages = "16973--16983",
abstract = "Hate speech detection has become an urgent task with the emergence of huge multimodal harmful content (, memes) on social media platforms. Previous studies mainly focus on complex feature extraction and fusion to learn discriminative information from memes. However, these methods ignore two key points: 1) the misalignment of image and text in memes caused by the modality gap, and 2) the uncertainty between modalities caused by the contribution degree of each modality to hate sentiment. To this end, this paper proposes an uncertainty-aware cross-modal alignment (UCA) framework for modeling the misalignment and uncertainty in multimodal hate speech detection. Specifically, we first utilize the cross-modal feature encoder to capture image and text feature representations in memes. Then, a cross-modal alignment module is applied to reduce semantic gaps between modalities by aligning the feature representations. Next, a cross-modal fusion module is designed to learn semantic interactions between modalities to capture cross-modal correlations, providing complementary features for memes. Finally, a cross-modal uncertainty learning module is proposed, which evaluates the divergence between unimodal feature distributions to to balance unimodal and cross-modal fusion features. Extensive experiments on five publicly available datasets show that the proposed UCA produces a competitive performance compared with the existing multimodal hate speech detection methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-uncertainty">
<titleInfo>
<title>Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chuanpeng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuqing</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaxin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jizhong</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songlin</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hate speech detection has become an urgent task with the emergence of huge multimodal harmful content (, memes) on social media platforms. Previous studies mainly focus on complex feature extraction and fusion to learn discriminative information from memes. However, these methods ignore two key points: 1) the misalignment of image and text in memes caused by the modality gap, and 2) the uncertainty between modalities caused by the contribution degree of each modality to hate sentiment. To this end, this paper proposes an uncertainty-aware cross-modal alignment (UCA) framework for modeling the misalignment and uncertainty in multimodal hate speech detection. Specifically, we first utilize the cross-modal feature encoder to capture image and text feature representations in memes. Then, a cross-modal alignment module is applied to reduce semantic gaps between modalities by aligning the feature representations. Next, a cross-modal fusion module is designed to learn semantic interactions between modalities to capture cross-modal correlations, providing complementary features for memes. Finally, a cross-modal uncertainty learning module is proposed, which evaluates the divergence between unimodal feature distributions to to balance unimodal and cross-modal fusion features. Extensive experiments on five publicly available datasets show that the proposed UCA produces a competitive performance compared with the existing multimodal hate speech detection methods.</abstract>
<identifier type="citekey">yang-etal-2024-uncertainty</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1475</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16973</start>
<end>16983</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection
%A Yang, Chuanpeng
%A Zhu, Fuqing
%A Liu, Yaxin
%A Han, Jizhong
%A Hu, Songlin
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yang-etal-2024-uncertainty
%X Hate speech detection has become an urgent task with the emergence of huge multimodal harmful content (, memes) on social media platforms. Previous studies mainly focus on complex feature extraction and fusion to learn discriminative information from memes. However, these methods ignore two key points: 1) the misalignment of image and text in memes caused by the modality gap, and 2) the uncertainty between modalities caused by the contribution degree of each modality to hate sentiment. To this end, this paper proposes an uncertainty-aware cross-modal alignment (UCA) framework for modeling the misalignment and uncertainty in multimodal hate speech detection. Specifically, we first utilize the cross-modal feature encoder to capture image and text feature representations in memes. Then, a cross-modal alignment module is applied to reduce semantic gaps between modalities by aligning the feature representations. Next, a cross-modal fusion module is designed to learn semantic interactions between modalities to capture cross-modal correlations, providing complementary features for memes. Finally, a cross-modal uncertainty learning module is proposed, which evaluates the divergence between unimodal feature distributions to to balance unimodal and cross-modal fusion features. Extensive experiments on five publicly available datasets show that the proposed UCA produces a competitive performance compared with the existing multimodal hate speech detection methods.
%U https://aclanthology.org/2024.lrec-main.1475
%P 16973-16983
Markdown (Informal)
[Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection](https://aclanthology.org/2024.lrec-main.1475) (Yang et al., LREC-COLING 2024)
ACL
- Chuanpeng Yang, Fuqing Zhu, Yaxin Liu, Jizhong Han, and Songlin Hu. 2024. Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 16973–16983, Torino, Italia. ELRA and ICCL.