Overview
- Provides background on the categories of dialogue systems, including their problems and weaknesses
- Provides a framework for open-world continual learning and explains how it can be used to improve dialogue systems
- Focuses on how lifelong learning dialogue systems can be built and deployed for practical applications
Part of the book series: Synthesis Lectures on Human Language Technologies (SLHLT)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (8 chapters)
Keywords
About this book
This book introduces the new paradigm of lifelong and continual learning dialogue systems to endow dialogue systems with the ability to learn continually by themselves through their own self-initiated interactions with their users and the working environments. The authors present the latest developments and techniques for building such continual learning dialogue systems. The book explains how these developments allow systems to continuously learn new language expressions, lexical and factual knowledge, and conversational skills through interactions and dialogues. Additionally, the book covers techniques to acquire new training examples for learning new tasks during the conversation. The book also reviews existing work on lifelong learning and discusses areas for future research.
Authors and Affiliations
About the authors
Sahisnu Mazumder is an AI Research Scientist at Intel Labs, USA, where he works on human-AI collaboration and dialogue and interactive systems research. He obtained his Ph.D. in Computer Science at the University of Illinois at Chicago, USA, and his Masters in Computer Science from the Indian Institute of Technology (IIT), Roorkee, India. His research interests include lifelong and continual learning, dialogue and interactive systems, open-world AI and learning, knowledge base reasoning, and sentiment analysis. He has published several research papers in these areas in leading AI, NLP and Dialogue conferences and given two tutorial talks on this book topic. During his Ph.D,, he also worked as a Research Intern at Microsoft Research Redmond and Huawei Research USA on virtual AI Assistants.
Bing Liu is a Distinguished Professor of Computer Science at the University of Illinois at Chicago, USA. He received his Ph.D. in Artificial Intelligence from the University of Edinburgh, UK. His research interests include lifelong and continual learning, lifelong learning dialogue systems, open-world learning, sentiment analysis and opinion mining, machine learning, and natural language processing. He has published extensively in top conferences and journals in these areas and has authored four books. Three of his papers have received Test-of-Time awards and another received Test-of-Time honorable mention. He is the winner of 2018 ACM SIGKDD Innovation Award and is a Fellow of AAAI, ACM, and IEEE.
Bibliographic Information
Book Title: Lifelong and Continual Learning Dialogue Systems
Authors: Sahisnu Mazumder, Bing Liu
Series Title: Synthesis Lectures on Human Language Technologies
DOI: https://doi.org/10.1007/978-3-031-48189-5
Publisher: Springer Cham
eBook Packages: Synthesis Collection of Technology (R0)
Copyright Information: The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2024
Hardcover ISBN: 978-3-031-48188-8Published: 10 January 2024
Softcover ISBN: 978-3-031-48191-8Due: 09 February 2024
eBook ISBN: 978-3-031-48189-5Published: 08 January 2024
Series ISSN: 1947-4040
Series E-ISSN: 1947-4059
Edition Number: 1
Number of Pages: XVI, 171
Number of Illustrations: 9 b/w illustrations, 55 illustrations in colour
Topics: Natural Language Processing (NLP), Artificial Intelligence, Machine Learning, Knowledge based Systems, Computational Linguistics, Computer Science, general