I am an associate professor in Natural Language Processing at the University of Stavanger, where I am part of the Information Access & Artificial Intelligence (IAI) research group. Previously, I was a researcher at the Université Grenoble Alpes and a member of Modélisation et Recherche d’Information Multimédia team, working with Philippe Mulhem and Lorraine Goeuriot. Before that, I was a postdoc at the University of Maryland working with Doug Oard. I was a member of UMIACS and the Computational Linguistics and Information Processing (CLIP) lab there. I completed my PhD in computational linguistics at the Institute of Formal and Applied Linguistics at Charles University in Prague where I was advised by Pavel Pecina.

I have been working on a wide range of information retrieval and natural language processing problems and I particularly enjoy working on interdisciplinary research and applications. My main research focus is cross-language information retrieval and multimedia, speech and video retrieval.

News

• 2/2026: We have a fully funded 3-year PhD position on an interdisciplinary project developing AI-based systems for clinical decision support, leveraging clinical text and multimodal data. Let me know if you are interested in further details.
• 1/2026 We are organizing a new RAG Task which will be a part of CLEF LongEval Track this year.
• 10/2025: I am serving as a Reproducibility Chair for ECIR 2026.
• 06/2025: I will be present at SIGIR 2025. I will be presenting a demo paper Navigating Speech Recording Collections with AI-Generated Illustrations done together with my bachelor students Sirina Håland and Trond Karlsen Strøm and Gabriel Iturra-Bocaz will be presenting at ICTIR our paper Impact of Shallow vs. Deep Relevance Judgments on BERT-based Reranking Models.
• 9/2024: I am happy to be a part of CLEF Steering Committee.
• 1/2024: I am looking for a Ph.D. student interested in working on an intersection of Information Retrieval and Large Language Models. If you are interested, please apply on Jobbnorge or reach out to ask any question.
• 9/2023: I started as an associate professor at the University of Stavanger, Department of Computer and Electrical Engineering, where I will be a part of the Information Access & Artificial Intelligence (IAI) research group.
• 6/2023: I serve as a lab chair at CLEF 2024.
• 5/2023: Two resource papers (LongEval-Retrieval: French-English Dynamic Test Collection for Continuous Web Search Evaluation and HC3: A Suite of Test Collections for CLIR Evaluation over Informal Text) and one demo paper (Exploratory Visualization Tool for the Continuous Evaluation of Information Retrieval Systems) accepted to SIGIR 2023.
• 12/2022: We are organizing LongEval Lab at CLEF 2023 focused on temporal persistence of information retrieval. Our paper describing the task (LongEval: Longitudinal Evaluation of Model Performance at CLEF 2023) was accepted to ECIR 2023.
• 05/2022: I won the Most Innovative Solution - Data Extraction prize at the NASA AI Risk Prediction Challenge. This was covered by major Slovak newspapers SME and Pravda.
• 05/2022: Our paper Multi-element protocol for IR experiments comparability: Application to the TREC-COVID test collection was accepted to the CIRCLE Conference.
• 06/2021: Our paper Tweets and Social Network Data for Twitter Bot Analysis was accepted to SBP-BRiMS.
• 05/2021: I am spending the summer at the SCALE summer camp at Johns Hopkins University.
• 05/2021: Our paper ‘Cross-language Sentence Selection via Data Augmentation and Rationale Training’ was accepted to ACL.
• 02/2021: I will be presenting the poster ‘Supporting Global Knowledge Sharing using Cross Language Information Retrieval’ at the Second AI and Data Science Workshop for Earth and Space Sciences.
• 01/2021: Our paper ‘Segmenting Subtitles for Correcting ASR Segmentation Errors’ was accepted to EACL.
• 11/2020: We achieved the highest scores in the TREC Podcasts Track organized by Spotify. Our report is available in the TREC proceedings.
• 05/2020: Proceedings of our Cross-Language Search and Summarization of Text and Speech workshop is available now and it contains our paper ‘MATERIALizing Cross-Language Information Retrieval: A Snapshot’ among others.
• 04/2020: Our paper ‘Combining Contextualized and Non-contextualized Query Translations to Improve CLIR’ was accepted to SIGIR.