Debiasing Multimodal Sarcasm Detection with Contrastive Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (16) · 18354-18362
DOI: 10.1609/aaai.v38i16.29795 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Mengzhao Jia und 2 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref).
Abstract (Originalsprache)
Despite commendable achievements made by existing work, prevailing multimodal sarcasm detection studies rely more on textual content over visual information. It unavoidably induces spurious correlations between textual words and labels, thereby significantly hindering the models' generalization capability. To address this problem, we define the task of out-of-distribution (OOD) multimodal sarcasm detection, which aims to evaluate models' generalizability when the word distribution is different in training and testing settings. Moreover, we propose a novel debiasing multimodal sarcasm detection framework with contrastive learning, which aims to mitigate the harmful effect of biased textual factors for robust OOD generalization. In particular, we first design counterfactual data augmentation to construct the positive samples with dissimilar word biases and negative samples with similar word biases. Subsequently, we devise an adapted debiasing contrastive learning mechanism to empower the model to learn robust task-relevant features and alleviate the adverse effect of biased words. Extensive experiments show the superiority of the proposed framework.
Zitieren
APA
Jia, M., Xie, C., & Jing, L. (2024). Debiasing Multimodal Sarcasm Detection with Contrastive Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16), 18354-18362. https://doi.org/10.1609/aaai.v38i16.29795
Vancouver
Jia M, Xie C, Jing L. Debiasing Multimodal Sarcasm Detection with Contrastive Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(16):18354-18362. doi:10.1609/aaai.v38i16.29795
BibTeX
@article{Jia2024,
author = {Jia, Mengzhao and Xie, Can and Jing, Liqiang},
title = {Debiasing Multimodal Sarcasm Detection with Contrastive Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {16},
pages = {18354--18362},
doi = {10.1609/aaai.v38i16.29795}
}
EUVIMED