Dialog as a Vehicle for Lifelong Learning

TL;DR

This paper discusses designing dialog systems that facilitate lifelong learning, especially for robots, by leveraging interactions to improve language understanding and machine learning systems over time.

Contribution

It highlights the importance of dialog as a vehicle for lifelong learning and outlines key challenges and prior work in developing such systems for robots.

Findings

Dialog interactions can be used to improve language understanding.

Lifelong learning in dialog systems remains an open challenge.

Applications in physically situated robots are particularly promising.

Abstract

Dialog systems research has primarily been focused around two main types of applications - task-oriented dialog systems that learn to use clarification to aid in understanding a goal, and open-ended dialog systems that are expected to carry out unconstrained "chit chat" conversations. However, dialog interactions can also be used to obtain various types of knowledge that can be used to improve an underlying language understanding system, or other machine learning systems that the dialog acts over. In this position paper, we present the problem of designing dialog systems that enable lifelong learning as an important challenge problem, in particular for applications involving physically situated robots. We include examples of prior work in this direction, and discuss challenges that remain to be addressed.