Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition

TL;DR

This paper introduces a novel multimodal Transformer framework with prompt learning to effectively handle missing modalities in sentiment analysis and emotion recognition, improving performance and robustness.

Contribution

The work proposes a new prompt learning approach with three prompt types to generate missing modality features and enhance multimodal learning.

Findings

Outperforms existing methods across all evaluation metrics.

Reduces the number of trainable parameters significantly.

Demonstrates robustness in handling various missing modality scenarios.

Abstract

The development of multimodal models has significantly advanced multimodal sentiment analysis and emotion recognition. However, in real-world applications, the presence of various missing modality cases often leads to a degradation in the model's performance. In this work, we propose a novel multimodal Transformer framework using prompt learning to address the issue of missing modalities. Our method introduces three types of prompts: generative prompts, missing-signal prompts, and missing-type prompts. These prompts enable the generation of missing modality features and facilitate the learning of intra- and inter-modality information. Through prompt learning, we achieve a substantial reduction in the number of trainable parameters. Our proposed method outperforms other methods significantly across all evaluation metrics. Extensive experiments and ablation studies are conducted to demonstrate the effectiveness and robustness of our method, showcasing its ability to effectively handle missing modalities.