Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysis

Abstract

Multimodal sentiment analysis (MSA) draws increasing attention with the availability of multimodal data. The boost in performance of MSA models is mainly hindered by two problems. On the one hand, recent MSA works mostly focus on learning cross-modal dynamics, but neglect to explore an optimal solution for unimodal networks, which determines the lower limit of MSA models. On the other hand, noisy information hidden in each modality interferes the learning of correct cross-modal dynamics. To address the above-mentioned problems, we propose a novel MSA framework \textbf{M}odulation \textbf{M}odel for \textbf{M}ultimodal \textbf{S}entiment \textbf{A}nalysis ({$M^{3}SA$}) to identify the contribution of modalities and reduce the impact of noisy information, so as to better learn unimodal and cross-modal dynamics. Specifically, modulation loss is designed to modulate the loss contribution based on the confidence of individual modalities in each utterance, so as to explore an optimal update solution for each unimodal network. Besides, contrary to most existing works which fail to explicitly filter out noisy information, we devise a modality filter module to identify and filter out modality noise for the learning of correct cross-modal embedding. Extensive experiments on publicly datasets demonstrate that our approach achieves state-of-the-art performance.

arXiv commentUpdated version

References in corpus (7)

• MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos
• Learning Factorized Multimodal Representations
• Neural Variational Inference and Learning in Belief Networks
• Learning Sparse Neural Networks through $L_0$ Regularization
• Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
• Analyzing Unaligned Multimodal Sequence via Graph Convolution and Graph Pooling Fusion