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

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.

arXiv commentProceedings of The Web Conference 2020

References in corpus (7)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Recurrent Neural Network for Text Classification with Multi-Task Learning
• MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos
• Efficient Low-rank Multimodal Fusion with Modality-Specific Factors
• Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities
• Investigation of Multimodal Features, Classifiers and Fusion Methods for Emotion Recognition
• Seq2Seq2Sentiment: Multimodal Sequence to Sequence Models for Sentiment Analysis