Deep Learning has revolutionized the academic research of conversational AI, models such as CNN intent extractors, DQN policy network, and LSTM language generators have been widely studied. Despite the potentials of scaling real-world conversational systems with these ML methods, not all of these approaches are ready for productions for various reasons.
In this talk, I will share the insights we have learned from building conversational agents in the academic setting, and how these unique experiences empower us to scale them across multiple application domains and languages with practical machine learning.
Tsung-Hsien (Shawn) Wen is a co-founder and Chief Scientist of PolyAI, a London-based startup looking to use the latest developments in NLP and ML to create a general platform for deploying spoken dialogue systems. He holds a PhD from the Dialogue Systems group, University of Cambridge, where he worked under the supervision of Professor Steve Young. His research focuses on language generation and end-to-end dialogue modeling, specifically in learning to generate responses for task-oriented dialogue systems. He was the tutor of the "Deep Learning and NLG" tutorial at INLG 2016 and has given invited seminars to research groups at Google, Apple, Xerox, and Baidu China. Before PolyAI, He was the invited lecturer for Samsung's corporate training course in Warsaw, a research consultant at IPSoft Amelia team, and a research intern at Google Brain.