Lifelong and Continual Learning Dialogue Systems: Learning during Conversation

Authors

  • Bing Liu University of Illinois at Chicago
  • Sahisnu Mazumder University of Illinois at Chicago

Keywords:

Dialogue Systems, Lifelong Learning, Continual Learning, Chatbots

Abstract

Dialogue systems, also called chatbots, are now used in a wide range of applications. However, they still have some major weaknesses. One key weakness is that they are typically trained from manually-labeled data and/or written with handcrafted rules, and their knowledge bases (KBs) are also compiled by human experts. Due to the huge amount of manual effort involved, they are difficult to scale and also tend to produce many errors ought to their limited ability to understand natural language and the limited knowledge in their KBs. Thus, the level of user satisfactory is often low. In this paper, we propose to dramatically improve the situation by endowing the chatbots the ability to continually learn (1) new world knowledge, (2) new language expressions to ground them to actions, and (3) new conversational skills, during conversation by themselves so that as they chat more and more with users, they become more and more knowledgeable and are better and better able to understand diverse natural language expressions and to improve their conversational skills.

Downloads

Published

2021-05-18

How to Cite

Liu, B., & Mazumder, S. (2021). Lifelong and Continual Learning Dialogue Systems: Learning during Conversation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17), 15058-15063. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17768

Issue

Section

Senior Member Presentation: Blue Sky Papers