Bring NLP to the Next Level: Lifelong language Learning

摘要:With the new DARPA program L2M (lifelong learning machine) and the new European Union Coordinated program LLIS (Lifelong Learning for Intelligent Systems), lifelong machine learning (LML) is coming to the center stage. Researchers and funding agencies have realized that the classic machine learning (ML) paradigm of simply running a ML algorithm on a given dataset is far from sufficient to bring true intelligence. It is only suitable for well-defined and narrow domains. In contrast, we humans learn very differently. We learn continuously in our interaction with the open environment, accumulate the learned knowledge, and use and adapt it to help future learning and problem solving. LML aims to achieve these capabilities. In NLP, chatbots and language-enabled robots are increasingly used in applications. It is highly desirable for these systems to learn continuously in their interaction with humans and other robots in the open world in a self-motivated and self-supervised manner to become more and more knowledgeable and better and better at chatting. In this talk, I will discuss this paradigm shift, some recent work on LML aimed at bringing NLP to the next level, and key challenges of LML.

简历:Bing Liu is a professor of Computer Science at the University of Illinois at Chicago. He received his Ph.D. in Artificial Intelligence from the University of Edinburgh. His research interests include lifelong machine learning, sentiment analysis, data mining, machine learning, and natural language processing. He has published extensively in top conferences and journals. Two of his papers have received 10-year Test-of-Time awards from KDD. He and his student co-authored the first ever book on lifelong machine learning in 2016. He also authored three other books: two on sentiment analysis and opinion mining, and one on Web data mining. Some of his research has been widely reported in the press, including a front-page article in the New York Times. On professional services, he serves as the Chair of ACM SIGKDD. He has served as program chair of many leading data mining conferences, including KDD, ICDM, CIKM, WSDM, SDM, and PAKDD, as associate editor of leading journals such as TKDE, TWEB, and DMKD, and as area chair or senior PC members of numerous natural language processing, AI, Web, and data mining conferences. He is a Fellow of ACM, AAAI and IEEE.