Together with ChengXiang Zhai, we will be giving our user simulation tutorial at AAAI’24 and WWW’24, customized to the respective audiences. The AAAI’24 edition adopts a broader perspective of user simulation for evaluating an interactive AI system and focuses more on simulation algorithms and techniques that are well connected with various sub-fields of AI, such as machine learning and agent-based systems. In contrast, the WWW’24 edition emphasizes more on applications of user simulation for evaluating Web information access systems, including click modeling and the application of simulation techniques in e-commerce.
Year: 2023
Tutorial on User Simulation @CIKM’23
I’m excited to share that, together with the esteemed ChengXiang Zhai, we’ll be presenting a tutorial on “User Simulation for Evaluating Information Access Systems” at the upcoming 32nd ACM International Conference on Information and Knowledge Management (CIKM ’23) in Birmingham, UK, in October. This half-day tutorial is based on our upcoming FnTIR book. We look forward to sharing our insights and also hope for feedback that could shape the final version of the book. Visit our companion website usersim.ai for more info.
User Simulation book draft available
I’m excited to share the draft of our book, co-authored by ChengXiang Zhai, User Simulation for Evaluating Information Access Systems: http://arxiv.org/abs/2306.08550
This book focuses on providing a thorough understanding of user simulation techniques designed specifically for evaluation purposes. We systematically review both general frameworks and specific models and algorithms for simulating user interactions with search engines, recommender systems, and conversational assistants.
We invite feedback on this first version. If you have suggestions, comments, pointers, etc. reach out to me in email!
Highlights from 2022
A selection of highlights from 2022:
- We organized ECIR’22 in Stavanger, Norway, marking it as the first major IR conference with a hybrid setup that allowed in-person travel after the pandemic. We wrote about our experiences in SIGIR Forum.
- Co-organized a workshop on Measuring the Quality of Explanations in Recommender Systems (SIGIR’22).
- Pioneered work on natural language user profiles for transparent and scrutable recommendation, published as a perspectives paper at SIGIR’22.
- Trond Linjordet successfully completed and defended his PhD thesis “A Critical Look at the Evaluation of Knowledge Graph Question Answering“.
- Two new PhD students started at IAI under my supervision: Nolwenn Bernard and Weronika Łajewska.
- Above all, I became a father this year, a personal milestone that far outshines any professional success. It has made me even more deliberate about where I spend my time, prompting me to say no more often, including accepting committee invitations and traveling to conferences.