Towards Learning Through Open-Domain Dialog

TL;DR

This paper explores the potential for open-domain dialog systems to learn from conversations, proposing generic methods for knowledge extraction, updating semantic networks, and grounding in actions to enable learning akin to humans.

Contribution

It identifies necessary modifications for dialog systems to learn from interactions and proposes generic approaches to implement these learning capabilities.

Findings

Outlined modifications needed for learning from dialog

Proposed generic approaches for knowledge extraction and updating

Highlighted the importance of grounding in actions and observations

Abstract

The development of artificial agents able to learn through dialog without domain restrictions has the potential to allow machines to learn how to perform tasks in a similar manner to humans and change how we relate to them. However, research in this area is practically nonexistent. In this paper, we identify the modifications required for a dialog system to be able to learn from the dialog and propose generic approaches that can be used to implement those modifications. More specifically, we discuss how knowledge can be extracted from the dialog, used to update the agent's semantic network, and grounded in action and observation. This way, we hope to raise awareness for this subject, so that it can become a focus of research in the future.