MInD: Improving Multimodal Sentiment Analysis via Multimodal Information Disentanglement

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dai, Weichen, Li, Xingyu, Wang, Zeyu, Hu, Pengbo, Qi, Ji, Peng, Jianlin, Zhou, Yi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929462328688640
author Dai, Weichen
Li, Xingyu
Wang, Zeyu
Hu, Pengbo
Qi, Ji
Peng, Jianlin
Zhou, Yi
author_facet Dai, Weichen
Li, Xingyu
Wang, Zeyu
Hu, Pengbo
Qi, Ji
Peng, Jianlin
Zhou, Yi
contents Learning effective joint representations has been a central task in multi-modal sentiment analysis. Previous works addressing this task focus on exploring sophisticated fusion techniques to enhance performance. However, the inherent heterogeneity of distinct modalities remains a core problem that brings challenges in fusing and coordinating the multi-modal signals at both the representational level and the informational level, impeding the full exploitation of multi-modal information. To address this problem, we propose the Multi-modal Information Disentanglement (MInD) method, which decomposes the multi-modal inputs into modality-invariant and modality-specific components through a shared encoder and multiple private encoders. Furthermore, by explicitly training generated noise in an adversarial manner, MInD is able to isolate uninformativeness, thus improves the learned representations. Therefore, the proposed disentangled decomposition allows for a fusion process that is simpler than alternative methods and results in improved performance. Experimental evaluations conducted on representative benchmark datasets demonstrate MInD's effectiveness in both multi-modal emotion recognition and multi-modal humor detection tasks. Code will be released upon acceptance of the paper.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11818
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MInD: Improving Multimodal Sentiment Analysis via Multimodal Information Disentanglement
Dai, Weichen
Li, Xingyu
Wang, Zeyu
Hu, Pengbo
Qi, Ji
Peng, Jianlin
Zhou, Yi
Multimedia
Learning effective joint representations has been a central task in multi-modal sentiment analysis. Previous works addressing this task focus on exploring sophisticated fusion techniques to enhance performance. However, the inherent heterogeneity of distinct modalities remains a core problem that brings challenges in fusing and coordinating the multi-modal signals at both the representational level and the informational level, impeding the full exploitation of multi-modal information. To address this problem, we propose the Multi-modal Information Disentanglement (MInD) method, which decomposes the multi-modal inputs into modality-invariant and modality-specific components through a shared encoder and multiple private encoders. Furthermore, by explicitly training generated noise in an adversarial manner, MInD is able to isolate uninformativeness, thus improves the learned representations. Therefore, the proposed disentangled decomposition allows for a fusion process that is simpler than alternative methods and results in improved performance. Experimental evaluations conducted on representative benchmark datasets demonstrate MInD's effectiveness in both multi-modal emotion recognition and multi-modal humor detection tasks. Code will be released upon acceptance of the paper.
title MInD: Improving Multimodal Sentiment Analysis via Multimodal Information Disentanglement
topic Multimedia
url https://arxiv.org/abs/2401.11818