Multimodal Multi-loss Fusion Network for Sentiment Analysis

TL;DR

This paper presents a multimodal neural network that optimally fuses features from multiple modalities and employs multi-loss training, significantly improving sentiment analysis accuracy across several datasets.

Contribution

It introduces a novel multi-loss fusion network that effectively combines multiple modalities and demonstrates the importance of context integration for sentiment detection.

Findings

Achieved state-of-the-art results on CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets.

Identified the impact of subnet performance and context on model accuracy.

Compared various fusion methods to determine optimal feature integration.

Abstract

This paper investigates the optimal selection and fusion of feature encoders across multiple modalities and combines these in one neural network to improve sentiment detection. We compare different fusion methods and examine the impact of multi-loss training within the multi-modality fusion network, identifying surprisingly important findings relating to subnet performance. We have also found that integrating context significantly enhances model performance. Our best model achieves state-of-the-art performance for three datasets (CMU-MOSI, CMU-MOSEI and CH-SIMS). These results suggest a roadmap toward an optimized feature selection and fusion approach for enhancing sentiment detection in neural networks.