Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal has remained elusive until recently. We are now observing promising results both in academia and industry, as large amounts of conversational data become available for training, and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI. In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems, or bots. The first is a question answering (QA) bot. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA bot can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat chatbot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender.
Michel Galley (Microsoft Research)
Michel Galley is a Senior Researcher at Microsoft Research AI. His research interests are in the areas of natural language processing and machine learning, with a particular focus on conversational AI, neural generation, statistical machine translation, and summarization. He obtained his M.S. and Ph.D. from Columbia University and his B.S. from EPFL, all in Computer Science. Before joining Microsoft Research, he was a Research Associate in the CS department at Stanford University. He was also a regular visiting researcher in the NLP group at USC/ISI and the Spoken Dialog Systems group at Bell Labs. He co-authored more than 50 scientific papers, many of which appeared at top NLP, AI, and ML conferences. Two of these publications were best paper finalists (NAACL 2010, EMNLP 2013). He also served as area chair at top NLP conferences (ACL, NAACL, EMNLP), and as a senior PC member at SIGIR and IJCAI.
Jianfeng Gao (Microsoft Research AI)
Jianfeng Gao is Partner Research Manager at Microsoft Research AI. He leads the development of AI systems for machine reading comprehension (MRC), question answering (QA), social bots, goal-oriented dialogue, and business applications. From 2014 to 2017, he was Partner Research Manager at Deep Learning Technology Center at Microsoft Research, Redmond, where he was leading the research on deep learning for text and image processing. From 2006 to 2014, he was Principal Researcher at Natural Language Processing Group at Microsoft Research, Redmond, where he worked on Web search, query understanding and reformulation, ads prediction, and statistical machine translation. From 2005 to 2006, he was a Research Lead in Natural Interactive Services Division at Microsoft, where he worked on Project X, an effort of developing natural user interface for Windows. From 2000 to 2005, he was Research Lead in Natural Language Computing Group at Microsoft Research Asia, where he and his colleagues developed the first Chinese speech recognition system released with Microsoft Office, the Chinese/Japanese Input Method Editors (IME) which were the leading products in the market, and the natural language platform for Microsoft Windows.