12th December (Full Day Tutorial)
Abstract: The tutorial will focus on the applications of neural network models—with shallow or deep architectures—on text-based search systems. The course plan for the lectures will follow a similar organization of topics as the book "An Introduction to Neural Information Retrieval" by Bhaskar Mitra and Nick Craswell. We begin the lecture by refreshing fundamental concepts in information retrieval and machine learning. We then introduce different neural and non-neural approaches for unsupervised learning of vector representations of text. Afterwards, we cover methods that employ these pre-trained neural vector representations to retrieval tasks. This will be followed by an introduction to the traditional Learning to Rank framework. Finally we conclude with a review of deep neural architectures and their applications to search tasks.
About the speaker: Bhaskar Mitra is a Principal Applied Scientist at Bing in the Microsoft Research Montreal lab. He joined Microsoft in 2006 and Bing—then called Live Search—in 2007. His research interests include machine learning and information retrieval, and in particular the topic of neural information retrieval (IR). He co-organized multiple workshops and tutorials, served as a guest editor for the special issue of the Information Retrieval Journal, and co-authored a book on the topic of neural IR. He is currently pursuing a part-time doctorate at University College London under the supervision of Dr. Emine Yilmaz and Dr. David Barber.