RE•WORK Deep Learning Summit

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.