Shifting Information Interactions

Modern information retrieval systems, such as search engines, recommender systems, and conversational agents, are best thought of as interactive systems, that is, systems that interact with and learn from user behavior. The ways in which people interact with information continue to change, with different devices, different presentation formats, and different information seeking scenarios. These changes give rise to new algorithmic and conceptual questions. For instance, how can we learn to rank good results if the display preferences are not known? How might we automatically generate questions to elicit a user's preferences so that an information retrieval system can adjust its results as efficiently as possible? And how should we understand information seeking dialogues? The talk is based on joint work with Claudio Di Ciccio, Julia Kiseleva, Harrie Oosterhuis, Filip Radlinski, Kate Revoredo, Anna Sepliarskaia, and Svitlana Vakulenko.