Building Neural Conversational Machines at Scale
Advances in deep learning have enabled us to build intelligent systems capable of perceiving and understanding real world from text, speech and images. Yet, building real-world Conversational AI systems at scale and from “scratch” remains a daunting challenge as it requires us to deal with ambiguity, data sparsity and solve complex language, dialog and generation problems.
In this talk, I will present powerful neural structured learning frameworks that tackle the above challenges by leveraging the power of deep learning combined with graphs which allow us to model the structure inherent in language and visual data. Our neural graph learning approach handles massive graphs with billions of vertices and trillions of edges and has been successfully used to power real-world applications such as Smart Reply, image recognition and multimodal experiences in many Google products both on Cloud and on-device. Finally, I will describe our recent work on reinforcement learning for controllable dialog generation, where we train a neural network that produces conversational responses conforming to specific semantic attributes such as sentiment, emotion and personality.
Dr. Sujith Ravi is a Senior Staff Research Scientist and Senior Manager at Google, where he leads the company’s large-scale graph-based machine learning platform and on-device machine learning efforts that power natural language understanding and image recognition for products used by millions of people everyday in Search, Gmail, Photos, Android, and YouTube. This technology powers Smart Reply to automatically suggests replies to incoming e-mails or chat messages in Gmail and Messages; Photos to search for anything from “hugs” to “dogs”; smart messaging directly from Android Wear smartwatches; and Learn2Compress platform for training custom on-device deep learning models. His research interests include large-scale inference, unsupervised and semi-supervised learning, on-device machine learning for IoT, conversational AI, computer vision, multimodal learning, and computational decipherment. Dr. Ravi has authored more than 70 scientific publications and patents in top-tier machine learning and natural language processing conferences, and his work won the ACM SIGKDD Best Research Paper Award in 2014. His work has been featured in Wired, Forbes, Forrester, NYTimes, TechCrunch, VentureBeat, Engadget, New Scientist, among others and he is a mentor for Google Launchpad startups. Dr. Ravi is the Co-Chair (AI & Deep Learning) for the 2019 National Academy of Engineering (NAE) German-American Frontiers of Engineering symposium. He was the Co-Chair for the NeurIPS 2018 On-device ML workshop and regularly serves as Area Chair and PC of top-tier machine learning and natural language processing conferences like NIPS, ICML, ACL, EMNLP, COLING, KDD, and WSDM.