A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis

TL;DR

This paper introduces a Transformer-based joint-encoding approach for simultaneous emotion recognition and sentiment analysis in multimodal language, utilizing co-attention and glimpse layers to effectively encode multiple modalities.

Contribution

It proposes a novel Transformer architecture with modular co-attention and glimpse layers for joint multimodal emotion and sentiment analysis, advancing the state-of-the-art in this area.

Findings

Submitted to ACL20 Grand-Challenge on Multimodal Language

Open-source code available for replication

Evaluated on CMU-MOSEI dataset

Abstract

Understanding expressed sentiment and emotions are two crucial factors in human multimodal language. This paper describes a Transformer-based joint-encoding (TBJE) for the task of Emotion Recognition and Sentiment Analysis. In addition to use the Transformer architecture, our approach relies on a modular co-attention and a glimpse layer to jointly encode one or more modalities. The proposed solution has also been submitted to the ACL20: Second Grand-Challenge on Multimodal Language to be evaluated on the CMU-MOSEI dataset. The code to replicate the presented experiments is open-source: https://github.com/jbdel/MOSEI_UMONS.