Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job
This addresses the issue of scalability and error-proneness in dialogue systems for users and developers, but it appears incremental as it builds on existing lifelong learning concepts applied to chatbots.
The paper tackles the problem of chatbots requiring extensive manual effort for training and knowledge base compilation, which limits scalability and leads to errors and low user satisfaction, by proposing a system that self-learns new world knowledge, language expressions, and conversational skills during interactions with users, aiming to improve performance over time.
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 this situation by endowing the system 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 or "on the job" by themselves so that as the systems 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 improve their conversational skills. A key approach to achieving these is to exploit the multi-user environment of such systems to self-learn through interactions with users via verb and non-verb means. The paper discusses not only key challenges and promising directions to learn from users during conversation but also how to ensure the correctness of the learned knowledge.