Application Keynote Lecture
Professor Emine Yilmaz (UCL)
From Search Queries to Conversations in the Design of Next Generation Information Access Systems
AbstractWith the introduction of new types of devices in our everyday lives such as intelligent assistants, the way people access information and their expectations have significantly changed. Most interactions now happen through conversations that happen over devices with small interfaces as opposed to search queries. This change has many implications in the design of information retrieval and access (IR) systems: we need to develop systems that can reduce the interactions needed with the device, while providing correct and unbiased information.
There are several research challenges that need to be overcome in devising such systems. In the first part of this talk, I will focus on the problems that need to be solved in designing IR systems that can reduce the user effort needed, as well as the progress that we have made in these areas. In the second part of the talk, I will emphasize the importance of detecting online misinformation and bias and describe some of the work we have done to tackle these issues. Finally, I will focus on the need for extensive manual annotations needed for training and evaluation of all these models and present Programmatic, a semi-automated annotation tool that significantly simplifies the process of obtaining annotations.
Emine Yilmaz is a Professor and Turing Fellow at University College London, Department of Computer Science. She also works as an Amazon Scholar for Amazon. Her research interests lie in the areas of information retrieval, data mining, and applications of machine learning, probability and statistics. She is a recipient of the Early Career Fellowship from the Engineering and Physical Sciences Research Council (EPSRC). To this date, she has received approximately 1.5 million GBP external funding from funding agencies including European Union, EPSRC, Google, Elsevier and Bloomberg. She has served in various senior roles, including co-editor-in-chief for the Information Retrieval Journal, a member of the editorial board for the AI Journal and an elected member of the executive committee for ACM SIGIR.