The paper titled "Personal Entity, Concept, and Named Entity Linking in Conversations" by Hideaki and Faegheh, has been accepted at CIKM 2022. Check out its arXiv version at https://arxiv.org/abs/2206.07836 if you are interested.
The paper titled "Find the Funding: Entity Linking with Incomplete Funding Knowledge Bases" by Faegheh, in collaboration with Gizem, Amin, and Georgios, has been accepted at COLING 2022. Check out its arXiv version at https://arxiv.org/abs/2209.00351 if you are interested.
The paper titled "On Success and Simplicity: A Second Look at Transferable Targeted Attacks" by Zhengyu, Zhuoran, and Martha has been accepted at NeurIPS 2021. Check out its arXiv version at https://arxiv.org/abs/2012.11207 if you are interested.
Harrie Oosterhuis from the Data Science group at iCIS received the best paper award at the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021) for his solo-authored paper titled "Computationally Efficient Optimization of Plackett-Luce Ranking Models for Relevance and Fairness". The paper can be found here.
Four Faculty of Science project teams have received a voucher of a maximum of €30.000 for an innovation and collaboration project relating to Green Information Technology. The research will be performed within the Radboud Centre for Green Information Technology, which is currently under establishment. The projects have been selected by a committee consisting of both internal members and external experts. In view of the high quality and quantity of the proposals, the Faculty Board has, by exception, approved four proposals, instead of three. One of winning projects was submitted by researchers from our Data Science department (Roel, Yuliya & TomH). For more details, follow this link.
In May 2021, four project teams originating from different faculties have received a voucher of a maximum of €20.000 for collaborative projects that contribute to the mission of Radboud AI: strengthening industrial collaboration and impact in the field of AI. Data Science researchers lead or are contributing to two of the granted projects: The right dose at the right time: AI for safe and effective paediatric drug use (Arjen & Martha)Detecting manmade structures from space (Konrad & TomC)The projects have been selected by a committee consisting of Radboud University and Radboudumc experts. In view of the high quality and quantity of the proposals, the Radboud AI Management Board has approved four proposals, instead of the planned three. For more details, follow this link.
The research proposal "Artificial Intelligent Based Damage Detection in Composite Materials" submitted to the Radboud - Glasgow Collaboration Fund has been accepted. The vision of this multidisciplinary project is to create a step change in visual inspection of large-scale composite structures by developing an Artificial Intelligence (AI)-based fully autonomous digitalized SHM platform. An AI-based platform will be developed in an effective, new collaboration between the University of Glasgow (UofG) and Radboud University (RU), to improve reliability and reduce inspection costs. The benefit of such technology will be experimentally demonstrated for inspection of aircrafts and wind turbine blades in close collaboration with the UK and Dutch industrial project partners.
The paper titled "Multi-view analysis of unregistered medicalimages using cross-view transformers" by Gijs, Yao and Elena has been accepted at the MICCAI 2021 conference, see https://www.miccai2021.org/en/.
The paper titled "Evaluating Diagnostic Content of AI-Generated Radiology Reports of Chest X-rays" by Zaheer, Twan and Elena in collaboration with Fabio Massimo Zanzotto, has been published in the journal "Artificial Intelligence in Medicine", see https://doi.org/10.1016/j.artmed.2021.102075.
The manuscript titled "Probabilistic modelling of gait for robust passive monitoring in daily life" by Luc and TomH, in collaboration with Yordan, Reham, Bas, Marjan, Kasper and Max, has been accepted for publication in the IEEE Journal of Biomedical and Health Informatics.