TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis

TL;DR

TransModality introduces an end-to-end Transformer-based fusion approach for multimodal sentiment analysis, effectively capturing subtle cross-modal correlations and achieving state-of-the-art results on multiple datasets.

Contribution

The paper proposes a novel end-to-end Transformer-based fusion method, TransModality, for multimodal sentiment analysis, leveraging translation between modalities to improve joint representations.

Findings

Achieves state-of-the-art performance on CMU-MOSI, MELD, IEMOCAP datasets.

Demonstrates effectiveness of translation-based fusion in multimodal sentiment analysis.

Validates the model's superiority over existing fusion methods.

Abstract

Multimodal sentiment analysis is an important research area that predicts speaker's sentiment tendency through features extracted from textual, visual and acoustic modalities. The central challenge is the fusion method of the multimodal information. A variety of fusion methods have been proposed, but few of them adopt end-to-end translation models to mine the subtle correlation between modalities. Enlightened by recent success of Transformer in the area of machine translation, we propose a new fusion method, TransModality, to address the task of multimodal sentiment analysis. We assume that translation between modalities contributes to a better joint representation of speaker's utterance. With Transformer, the learned features embody the information both from the source modality and the target modality. We validate our model on multiple multimodal datasets: CMU-MOSI, MELD, IEMOCAP. The experiments show that our proposed method achieves the state-of-the-art performance.