Lifelong and Continual Learning Dialogue Systems
Sahisnu Mazumder, Bing Liu

TL;DR
This paper discusses lifelong learning dialogue systems that enable chatbots to continually improve through self-initiated interactions, reducing reliance on manual data and knowledge base updates.
Contribution
It introduces a new paradigm for dialogue systems that learn continuously from interactions, presenting recent techniques and surveying existing work in this area.
Findings
Systems can learn new language expressions during conversations.
Dialogue systems acquire factual knowledge from external sources.
Continual learning enhances chatbot knowledge and conversational skills.
Abstract
Dialogue systems, commonly known as chatbots, have gained escalating popularity in recent times due to their wide-spread applications in carrying out chit-chat conversations with users and task-oriented dialogues to accomplish various user tasks. Existing chatbots are usually trained from pre-collected and manually-labeled data and/or written with handcrafted rules. Many also use manually-compiled knowledge bases (KBs). Their ability to understand natural language is still limited, and they tend to produce many errors resulting in poor user satisfaction. Typically, they need to be constantly improved by engineers with more labeled data and more manually compiled knowledge. This book introduces the new paradigm of lifelong learning dialogue systems to endow chatbots the ability to learn continually by themselves through their own self-initiated interactions with their users and working…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech and dialogue systems · Topic Modeling · AI in Service Interactions
