Monthly Archives: September 2017

Short bio

Dr. Sujith Ravi, a Staff Research Scientist and Manager at Google, leads the company’s large-scale graph-based machine learning platform that powers natural language understanding and image recognition for products used by millions of people everyday in Search, Gmail, Photos, Android, YouTube, and Allo. The machine learning technology enables features such as Smart Reply that automatically suggests replies to incoming e-mails or chat messages in Inbox and Allo; Photos that searches for anything, from “hugs” to “dogs,” with the latest image recognition system; and smart messaging directly from Android Wear smartwatches powered by on-device machine learning.

Dr. Ravi has authored more than 50 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. He organizes machine learning symposia/workshops and regularly serves as Area Chair and PC of top-tier machine learning and natural language processing conferences.

Talk abstract

Neural Graph Learning

Recent machine learning advances have enabled us to build intelligent systems that understand semantics from speech, natural language text and images. While great progress has been made in many AI fields, building scalable intelligent systems from “scratch” still remains a daunting challenge for many applications.To overcome this, we exploit the power of graph algorithms since they offer a simple elegant way to express different types of relationships observed in data and can concisely encode structure underlying a problem. In this talk I will focus on “How can we combine the flexibility of graphs with the power of machine learning?”

I will describe how we address these challenges and design efficient algorithms by employing graph-based machine learning as a computing mechanism to solve real-world prediction tasks. Our graph-based machine learning framework can operate at large scale and easily handle massive graphs (containing billions of vertices and trillions of edges) and make predictions over billions of output labels while achieving O(1) space complexity per vertex. In particular, we combine graph learning with deep neural networks to power a number of machine intelligence applications, including Smart Reply, image recognition and video summarization to tackle complex language understanding and computer vision problems. l will also introduce some of our latest research and share results on “neural graph learning”, a new joint optimization framework for combining graph learning with deep neural network models.

Short bio

After leading and managing the AWS Deep Learning group at Amazon that was responsible for building and solving natural language processing and dialog applications (2016–2017), as of December 2017 Dr. Zornitsa Kozareva has taken a managerial position at Google. From 2014 to 2016 she was a Senior Manager at Yahoo! leading the Query Processing group that powered Mobile Search and Advertisement. Earlier, during the period 2009–2014, Dr. Kozareva wore an academic hat as Research Professor at the University of Southern California CS Department with affiliation to Information Sciences Institute where she spearheaded research funded by DARPA and IARPA on learning to read, interpreting metaphors and building knowledge bases from the Web.

Dr. Kozareva regularly serves as Area Chair and PC of top-tier NLP conferences. She has organized four SemEval scientific challenges and has published over 80 research papers. Dr. Kozareva is a recipient of the John Atanasoff Award given by the President of Republic of Bulgaria in 2016 for her contributions and impact in science, education, and industry; the Yahoo! Labs Excellence Award in 2014 and the RANLP Young Scientist Award in 2011.

Talk abstract

Building Conversational Assistants using Deep Learning

Over the years there has been a paradigm shift in how humans interact with machines. Today’s users are no longer satisfied with seeing a list of relevant web pages, instead they want to complete tasks and take actions. This raises the questions: “How do we teach machines to become useful in a human-centered environment?” and “How do we build machines that help us organize our daily schedules, arrange our travel and be aware of our preferences and habits?”. In this talk, I will describe these challenges in the context of conversational assistants. Then, I will delve into deep learning algorithms for entity extraction, user intent prediction and question answering. Finally, I will highlight findings on user intent prediction from shopping, movies, restaurant and sport domains.