Introducing Brain-like Concepts to Embodied Hand-crafted Dialog Management System

TL;DR

This paper introduces a neurobiologically inspired behavior engine for embodied dialog systems, combining hand-crafted models with neural networks to enable more natural and flexible human-machine interactions.

Contribution

It presents a novel neural behavior engine that integrates concepts from neurobiology into dialog management, bridging hand-crafted and neural approaches.

Findings

Demonstrated a virtual receptionist using the proposed architecture

Showed the feasibility of mixed initiative dialog with brain-like behavior models

Validated the approach in a semi-public space environment

Abstract

Along with the development of chatbot, language models and speech technologies, there is a growing possibility and interest of creating systems able to interface with humans seamlessly through natural language or directly via speech. In this paper, we want to demonstrate that placing the research on dialog system in the broader context of embodied intelligence allows to introduce concepts taken from neurobiology and neuropsychology to define behavior architecture that reconcile hand-crafted design and artificial neural network and open the gate to future new learning approaches like imitation or learning by instruction. To do so, this paper presents a neural behavior engine that allows creation of mixed initiative dialog and action generation based on hand-crafted models using a graphical language. A demonstration of the usability of such brain-like inspired architecture together with a graphical dialog model is described through a virtual receptionist application running on a semi-public space.