no code implementations • EMNLP 2020 • Annie Louis, Dan Roth, Filip Radlinski
We revisit a pragmatic inference problem in dialog: Understanding indirect responses to questions.
no code implementations • 26 Jul 2023 • Scott Sanner, Krisztian Balog, Filip Radlinski, Ben Wedin, Lucas Dixon
Inspired by recent successes of prompting paradigms for large language models (LLMs), we study their use for making recommendations from both item-based and language-based preferences in comparison to state-of-the-art item-based collaborative filtering (CF) methods.
no code implementations • 16 Mar 2023 • Krisztian Balog, Filip Radlinski, Andrey Petrov
Despite the potential impact of explanations on decision making, there is a lack of research on quantifying their effect on users' choices.
1 code implementation • 13 Mar 2023 • Arun Tejasvi Chaganty, Megan Leszczynski, Shu Zhang, Ravi Ganti, Krisztian Balog, Filip Radlinski
Users in consumption domains, like music, are often able to more efficiently provide preferences over a set of items (e. g. a playlist or radio) than over single items (e. g. songs).
no code implementations • 27 Jan 2023 • Megan Leszczynski, Shu Zhang, Ravi Ganti, Krisztian Balog, Filip Radlinski, Fernando Pereira, Arun Tejasvi Chaganty
This has motivated conversational recommender systems (CRSs), with control provided through natural language feedback.
1 code implementation • 21 Dec 2022 • Mohammad Javad Hosseini, Filip Radlinski, Silvia Pareti, Annie Louis
We address this problem of reference resolution, when people use natural expressions to choose between the entities.
no code implementations • 19 May 2022 • Filip Radlinski, Krisztian Balog, Fernando Diaz, Lucas Dixon, Ben Wedin
Natural interaction with recommendation and personalized search systems has received tremendous attention in recent years.
no code implementations • 21 Jan 2022 • Hamed Zamani, Johanne R. Trippas, Jeff Dalton, Filip Radlinski
Conversational information seeking (CIS) is concerned with a sequence of interactions between one or more users and an information system.
1 code implementation • 26 Nov 2021 • Ivica Kostric, Krisztian Balog, Filip Radlinski
These strategies do not perform well in cases where the user does not have sufficient knowledge of the target domain to answer such questions.
no code implementations • 19 May 2021 • Krisztian Balog, Filip Radlinski, Alexandros Karatzoglou
We address how to robustly interpret natural language refinements (or critiques) in recommender systems.
no code implementations • 1 Jan 2021 • Preksha Nema, Alexandros Karatzoglou, Filip Radlinski
Untangle gives control on critiquing recommendations based on users preferences, without sacrificing on recommendation accuracy.
no code implementations • 7 Oct 2020 • Annie Louis, Dan Roth, Filip Radlinski
We revisit a pragmatic inference problem in dialog: understanding indirect responses to questions.
no code implementations • 19 Jan 2020 • Krisztian Balog, Lucie Flekova, Matthias Hagen, Rosie Jones, Martin Potthast, Filip Radlinski, Mark Sanderson, Svitlana Vakulenko, Hamed Zamani
This paper discusses the potential for creating academic resources (tools, data, and evaluation approaches) to support research in conversational search, by focusing on realistic information needs and conversational interactions.
no code implementations • WS 2019 • Filip Radlinski, Krisztian Balog, Bill Byrne, Karthik Krishnamoorthi
Studying the dialogues in one domain, we present a brief quantitative analysis of how people describe movie preferences at scale.
no code implementations • NeurIPS 2008 • Deepayan Chakrabarti, Ravi Kumar, Filip Radlinski, Eli Upfal
In our model, arms have (stochastic) lifetime after which they expire.
no code implementations • International Conference on Machine Learning 2008 • Filip Radlinski, Robert Kleinberg, Thorsten Joachims
Algorithms for learning to rank Web documents usually assume a document's relevance is independent of other documents.