Abstract: 

As increasingly larger proportions of users interact with online services like search engines and recommender systems to satisfy their information needs, developing better understanding of user interactions becomes important for improving user experience and gauging user satisfaction. In this talk, I will focus on different aspects of user behavior, and present algorithms that learn from user interactions. Starting with understanding user’s information needs, I will present state-of-the-art techniques which aim at extracting tasks from a collection of search log data. The mined knowledge from log activity data reveals users' underlying intentions and interests, which provide unique signals for human centric optimization and personalization. I will discuss different ways of building user models which leverage such behavioral signals. Finally, I will touch upon novel deep sequential models which leverage user interaction sequences to detect implicit measures of user satisfaction. Throughout the talk, we present insights from experiments with tera-scale user interaction data from search engines and digital assistants including Microsoft Cortana.

Bio: 

Rishabh Mehrotra is a final year PhD student at University College London partially supported by a Google Research Award. His PhD research focuses on inference of search tasks from query logs and their applications. Beyond tasks, his research interests include user modelling & personalization, counterfactual analysis and deep learning for gauging user satisfaction. Some of his recent work has been published at top conferences including WWW, SIGIR, NAACL, CIKM, RecSys and WSDM. He has supervised over 10 Masters thesis and has served as a reviewer for top tier conferences and workshops. Over the past few years, Rishabh has been working closely with leading industrial researchers at Microsoft Research, LinkedIn & NICTA on interesting machine learning & data science projects and has given over 20 invited talks and seminars. He is also a co-coordinator of the TREC Tasks Track in 2015, 2016 and 2017 and co-tutored a tutorial at Search Solutions 2016 conference.