A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis
Computation and Language
2020-08-11 v1 Human-Computer Interaction
Machine Learning
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.
Cite
@article{arxiv.2006.15955,
title = {A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis},
author = {Jean-Benoit Delbrouck and Noé Tits and Mathilde Brousmiche and Stéphane Dupont},
journal= {arXiv preprint arXiv:2006.15955},
year = {2020}
}
Comments
Winner of the ACL20: Second Grand-Challenge on Multimodal Language