Multimodal fusion via cortical network inspired losses

Shiv Shankar


Abstract
Information integration from different modalities is an active area of research. Human beings and, in general, biological neural systems are quite adept at using a multitude of signals from different sensory perceptive fields to interact with the environment and each other. Recent work in deep fusion models via neural networks has led to substantial improvements over unimodal approaches in areas like speech recognition, emotion recognition and analysis, captioning and image description. However, such research has mostly focused on architectural changes allowing for fusion of different modalities while keeping the model complexity manageable.Inspired by neuroscientific ideas about multisensory integration and processing, we investigate the effect of introducing neural dependencies in the loss functions. Experiments on multimodal sentiment analysis tasks with different models show that our approach provides a consistent performance boost.
Anthology ID:
2022.acl-long.83
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1167–1178
Language:
URL:
https://aclanthology.org/2022.acl-long.83
DOI:
10.18653/v1/2022.acl-long.83
Bibkey:
Cite (ACL):
Shiv Shankar. 2022. Multimodal fusion via cortical network inspired losses. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1167–1178, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Multimodal fusion via cortical network inspired losses (Shankar, ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.83.pdf