Towards Teachable Conversational Agents

TL;DR

This paper explores the development of conversational agents that can learn interactively from human teachers, aiming to improve teachability and compare conversational learning with traditional supervised methods.

Contribution

It introduces the concept of teachable conversational agents and investigates their ability to learn reliably through dialogue, highlighting key factors for development.

Findings

Teachable conversational agents can learn effectively from human interaction.

Conversational learning shows comparable performance to traditional supervised learning.

Factors influencing successful conversational teaching are identified.

Abstract

The traditional process of building interactive machine learning systems can be viewed as a teacher-learner interaction scenario where the machine-learners are trained by one or more human-teachers. In this work, we explore the idea of using a conversational interface to investigate the interaction between human-teachers and interactive machine-learners. Specifically, we examine whether teachable AI agents can reliably learn from human-teachers through conversational interactions, and how this learning compare with traditional supervised learning algorithms. Results validate the concept of teachable conversational agents and highlight the factors relevant for the development of machine learning systems that intend to learn from conversational interactions.