Dialog Policy Learning for Joint Clarification and Active Learning Queries

Authors

  • Aishwarya Padmakumar Amazon Alexa AI
  • Raymond J. Mooney University of Texas at Austin

Keywords:

Conversational AI/Dialog Systems, Language and Vision, Active Learning

Abstract

Intelligent systems need to be able to recover from mistakes, resolve uncertainty, and adapt to novel concepts not seen during training. Dialog interaction can enable this by the use of clarifications for correction and resolving uncertainty, and active learning queries to learn new concepts encountered during operation. Prior work on dialog systems has either focused on exclusively learning how to perform clarification/ information seeking, or to perform active learning. In this work, we train a hierarchical dialog policy to jointly perform {\it both} clarification and active learning in the context of an interactive language-based image retrieval task motivated by an online shopping application, and demonstrate that jointly learning dialog policies for clarification and active learning is more effective than the use of static dialog policies for one or both of these functions.

Downloads

Published

2021-05-18

How to Cite

Padmakumar, A., & Mooney, R. J. (2021). Dialog Policy Learning for Joint Clarification and Active Learning Queries. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13604-13612. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17604

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing II