Towards a Neuro-Symbolic Framework for Multimodal Human-AI Interaction

Anthony Scotte, Varuna De Silva

2023

Abstract

Humans are not defined by a single means of communication: language, style, expression, body posture, emotion and attitude all contribute to the mix that makes communicating challenging to understand. As humans seek to strengthen partnerships with computers, these communication complexities need to be both understood and overcome. This paper seeks to explore a framework that combines neural networks with decision theory and probabilistic logic to tackle the complexities inherent within conversational communication. In combining the strength of each of these capabilities through a proof of concept, this paper demonstrates a potential framework of how different AI models may deepen its understanding of human conversation.

Paper Citation

in Harvard Style

Scotte A. and De Silva V. (2023). Towards a Neuro-Symbolic Framework for Multimodal Human-AI Interaction. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 932-939. DOI: 10.5220/0011776300003411

in Bibtex Style

@conference{icpram23,
author={Anthony Scotte and Varuna De Silva},
title={Towards a Neuro-Symbolic Framework for Multimodal Human-AI Interaction},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={932-939},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011776300003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Towards a Neuro-Symbolic Framework for Multimodal Human-AI Interaction
SN - 978-989-758-626-2
AU - Scotte A.
AU - De Silva V.
PY - 2023
SP - 932
EP - 939
DO - 10.5220/0011776300003411