CIIR Talk Series: Evangelos Kanoulas

Speaker: Evangelos Kanoulas, Professor at University of Amsterdam

Talk Title: From sessions to conversations and back again

Date: Friday, November 20, 2020 - 11:00 AM - 12:00 PM EST (North American Eastern Standard Time) via Zoom

Zoom Access: Zoom Link and reach out to Alex Taubman for the passcode.

Abstract: In this talk I will discuss my recent project on Conversational Search Engines (ConverSE) describing the various efforts being made along three different aspects of conversational search: open-ended question answering, conversational question answering, and mixed initiative conversations. I will look at the problems not only from an algorithmic perspective, but also from an evaluation perspective. Preceding the discussion about conversational search, I will describe some of the earlier efforts made to connect system-oriented and user-oriented consideration of search engines. Having discussed conversational search and recommendation I will go back to the research questions raised by the now forgotten TREC Tasks and Sessions tracks, which I still consider relevant and open.

Bio: Evangelos Kanoulasis a professor of computer science at the University of Amsterdam, leading the IRLab at the Informatics Institute. His research focuses on developing evaluation methods and algorithms for search and recommendation. He has always been an advocate of bridging the system-oriented consideration of search with the human-oriented perspective. On this basis he was one of organizers of the TREC Session and the TREC Tasks tracks. He has also participated in the coordination of the TREC Million Query, the TREC Common Core, and the CLEF e-Health tracks. Currently, he is leading a team of 8 PhD students and 2 postdocs. His research has been published at SIGIR, CIKM, KDD, WWW, WSDM, and other venues in the fields of IR and RecSys. Furthermore, he is a member of the Ellis society, and a co-founder of Ellogon AI a company that focuses on personalizing immunotherapy with the power of big and rich data and cutting-edge AI algorithms.