Talk Title: Bridging the Gap: Industrial Dialog Framework vs Deep Learning-based Dialog Systems
Abstract: There have been tremendous advances in building dialog systems that use past human to human conversation logs and apply deep learning-based techniques on them for learning dialog models. At the same time, several frameworks for building chat-bots have been released by different enterprises such as Google Dialog Flow, IBM Watson Assistant and Microsoft Bot framework. In this talk, I would illustrate the gap that exist in these two parallel threads of work and show how we could apply deep learning based techniques in the context of industry frameworks to get the best of both worlds.
Bio: Sachindra Joshi is a distinguished Engineer and manages the AI for Interaction department at IBM India Research Lab that focuses on research in natural language processing, conversation modeling, process mining and automation. He also leads the conversation AI effort across IBM research and work closely with different labs and business divisions to create state-of-the-art conversation technologies and integrate them with IBM products and services. He has over 70 research papers in top journals and conferences. He also has over 50 patents to his name. Prior to joining IBM research, Sachindra completed Masters in Computer Science and Engineering from Indian Institute of Technology, Bombay in year 2000.