Publications

The PKG API is a tool for managing personal knowledge graphs (PKGs), which has been developed by our group (Nolwenn Bernard, Ivica Kostric, Weronika Łajewska, Krisztian Balog, Petra Galuscakova, Vinay Setty, and Martin G. Skjæveland). This work is a first step toward the realization of our proposed PKG ecosystem and has been presented at the 2024 ACM Web Conference, in Singapore. Have a look at the paper or the toolkit for more details.

Our group has the following papers accepted at SIGIR’24:

• Explainability for Transparent Conversational Information-Seeking — full paper by Weronika Łajewska, Damiano Spina, Johanne Trippas and Krisztian Balog
• A Surprisingly Simple yet Effective Multi-Query Rewriting Method for Conversational Passage Retrieval — short paper by Ivica Kostric and Krisztian Balog
• The Surprising Effectiveness of Rankers trained on Expanded Queries — short paper by Abhijit Anand, Venktesh V, Vinay Setty and Avishek Anand
• Dataset and Models for Item Recommendation Using Multi-Modal User Interactions — resource paper by Simone Borg Bruun, Krisztian Balog, and Maria Maistro
• QuantTemp: A Real-world Open-domain Benchmark for Fact-checking Numerical Claims — resource paper by Venktesh V, Abhijit Anand, Avishek Anand and Vinay Setty
• FactCheck Editor: Multilingual Text Editor with End-to-End fact-checking — demo paper by Vinay Setty

In addition, our group is also involved with the organization of the Simulations for Information Access (Sim4IA) workshop.

Preprints will follow soon.

IAI MovieBot is a conversational recommender system for movies developed by members of our group, Javeria Habib, Krisztian Balog, Nolwenn Bernard, Ivica Kostric, Weronika Łajewska, Martin G. Skjæveland, and Shuo Zhang. This work has been demonstrated at the 17th ACM International Conference on Web Search and Data Mining (WSDM’24), in Merida, Mexico. Have a look at the demo paper or the repository to learn more about our movie recommender system.

The paper An Ecosystem for Personal Knowledge Graphs: A Survey and Research Roadmap by Martin G. Skjæveland, Krisztian Balog, Nolwenn Bernard, Weronika Łajewska, and Trond Linjordet has been accepted for publication in AI Open and is now available online.

The paper A Systematic Review of Fairness, Accountability, Transparency and Ethics in Information Retrieval by Nolwenn Bernard and Krisztian Balog has been accepted by ACM Computing Surveys and is now available online.

Some recent papers acceptances on conversational search:

• Towards Reliable and Factual Response Generation: Detecting Unanswerable Questions in Information-seeking Conversations — short paper at ECIR’24 by Weronika Łajewska and Krisztian Balog [PDF]
• Estimating the Usefulness of Clarifying Questions and Answers for Conversational Search — short paper at ECIR’24 by Ivan Sekulic, Weronika Łajewska, Krisztian Balog, and Fabio Crestani [PDF]
• Towards Self-Contained Answers: Entity-Based Answer Rewriting in Conversational Search — full paper at CHIIR’24 by Ivan Sekulic, Krisztian Balog, and Fabio Crestani [PDF]

The paper Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systems by Ivica Kostric, Krisztian Balog, and Filip Radlinski has been accepted by ACM Transactions on Recommender Systems and is now available online.

Our group has two contributions accepted at CIKM’23:

• Towards Filling the Gap in Conversational Search: From Passage Retrieval to Conversational Response Generation — resource paper by Weronika Łajewska and Krisztian Balog [PDF]
• Tutorial on User Simulation for Evaluating Information Access Systems — tutorial by Krisztian Balog and ChengXiang Zhai [website]

Trustworthy journalism through AI, co-authored by Vinay Setty, has been accepted in the Data & Knowledge Engineering journal and is now available here.

MG-ShopDial: A Multi-Goal Conversational Dataset for e-Commerce by Nolwenn Bernard and Krisztian Balog has been accepted at the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR’23) as a resource paper.