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

Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque, Sarah Masud Preum


Abstract
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.
Anthology ID:
2024.eacl-srw.12
Volume:
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Neele Falk, Sara Papi, Mike Zhang
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
162–174
Language:
URL:
https://aclanthology.org/2024.eacl-srw.12
DOI:
Bibkey:
Cite (ACL):
Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque, and Sarah Masud Preum. 2024. Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 162–174, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection (Hossain et al., EACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.eacl-srw.12.pdf
Video:
 https://aclanthology.org/2024.eacl-srw.12.mp4