Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hossain, Eftekhar, Sharif, Omar, Hoque, Mohammed Moshiul, Preum, Sarah M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917590807347200
author Hossain, Eftekhar
Sharif, Omar
Hoque, Mohammed Moshiul
Preum, Sarah M.
author_facet Hossain, Eftekhar
Sharif, Omar
Hoque, Mohammed Moshiul
Preum, Sarah M.
contents Multimodal hateful content detection is a challenging task that requires complex reasoning across visual and textual modalities. Therefore, creating a meaningful multimodal representation that effectively captures the interplay between visual and textual features through intermediate fusion is critical. Conventional fusion techniques are unable to attend to the modality-specific features effectively. Moreover, most studies exclusively concentrated on English and overlooked other low-resource languages. This paper proposes a context-aware attention framework for multimodal hateful content detection and assesses it for both English and non-English languages. The proposed approach incorporates an attention layer to meaningfully align the visual and textual features. This alignment enables selective focus on modality-specific features before fusing them. We evaluate the proposed approach on two benchmark hateful meme datasets, viz. MUTE (Bengali code-mixed) and MultiOFF (English). Evaluation results demonstrate our proposed approach's effectiveness with F1-scores of $69.7$% and $70.3$% for the MUTE and MultiOFF datasets. The scores show approximately $2.5$% and $3.2$% performance improvement over the state-of-the-art systems on these datasets. Our implementation is available at https://github.com/eftekhar-hossain/Bengali-Hateful-Memes.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09738
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection
Hossain, Eftekhar
Sharif, Omar
Hoque, Mohammed Moshiul
Preum, Sarah M.
Computation and Language
Multimodal hateful content detection is a challenging task that requires complex reasoning across visual and textual modalities. Therefore, creating a meaningful multimodal representation that effectively captures the interplay between visual and textual features through intermediate fusion is critical. Conventional fusion techniques are unable to attend to the modality-specific features effectively. Moreover, most studies exclusively concentrated on English and overlooked other low-resource languages. This paper proposes a context-aware attention framework for multimodal hateful content detection and assesses it for both English and non-English languages. The proposed approach incorporates an attention layer to meaningfully align the visual and textual features. This alignment enables selective focus on modality-specific features before fusing them. We evaluate the proposed approach on two benchmark hateful meme datasets, viz. MUTE (Bengali code-mixed) and MultiOFF (English). Evaluation results demonstrate our proposed approach's effectiveness with F1-scores of $69.7$% and $70.3$% for the MUTE and MultiOFF datasets. The scores show approximately $2.5$% and $3.2$% performance improvement over the state-of-the-art systems on these datasets. Our implementation is available at https://github.com/eftekhar-hossain/Bengali-Hateful-Memes.
title Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection
topic Computation and Language
url https://arxiv.org/abs/2402.09738