CIIR Talk Series

Title: User Intent Prediction for Conversational Intelligent Assistants

Abstract: As conversational assistants aim to operate in increasingly complex domains, predicting user intent remains a critical and still unsolved first step for a conversational system. I will describe the different dimensions of this challenge, including some recent progress on representation of context and domain knowledge for open domain conversations, recommender systems, and e-commerce. Intent prediction becomes even more difficult as conversational assistants attempt to guide users with tasks in the physical world, such as the current Alexa Prize Task Assistance challenge on assisting with cooking and home improvement, which illustrates exciting research challenges and opportunities to come.

Bio: Eugene Agichtein is a Winship Professor of Computer Science at Emory University in Atlanta, USA, where he leads the Intelligent Information Access Laboratory (IR Lab). Since January 2019, he has also been an "Amazon Scholar" (~principal scientist) at Alexa Shopping. Eugene's research spans the areas of information retrieval, natural language processing, data mining, and human computer interaction, most recently focusing on conversational search and recommendation. His work with colleagues and students has been recognized by multiple awards, including A.P. Sloan Fellowship, the 2013 Karen Spark Jones Award from the British Computer Society, and "test of time" and best paper awards at SIGIR, WSDM and SIGMOD. Eugene was PC Co-Chair of WWW 2017, WSDM 2012 and 2021 and currently CIKM 2022.

To attend this talk via Zoom, click here. Participants will need a passcode to attend this event. If you need the passcode for this series, please see the event advertisement on the seminars email list or reach out to Alex Taubman. For any questions about this event with the Center for Intelligent Information Retrieval, please contact Jean Joyce.