Источник
ECIR
Дата публикации
06.04.2025
Авторы
Anastasios Nentidis Georgios Katsimpras Anastasia Krithara Martin Krallinger Miguel Rodriguez Ortega Natalia Loukachevitch Андрей Саховский Елена Тутубалина Grigorios Tsoumakas George Giannakoulas Alexandra Bekiaridou Athanasios Samaras Giorgio Maria Di Nunzio Nicola Ferro Stefano Marchesin Laura Menotti Gianmaria Silvello Georgios Paliouras
Поделиться

BioASQ at CLEF2025: The thirteenth edition of the large-scale biomedical semantic indexing and question answering challenge

Аннотация

During the last twelve years, the large-scale biomedical semanticindexing and question-answering challenge (BioASQ) has beenpushing towards the continuous advancement of methods and tools to accelerateaccess to the ever-increasing scientific resources of the biomedicaldomain. In this direction, each year, BioASQ organizes shared tasks representingthe real information needs of biomedical experts and providesrespective benchmark datasets. This way, it provides a unique commontestbed where research teams around the world can test and comparenew approaches for accessing biomedical knowledge.The thirteenth version of BioASQ will be held as an evaluation Lab inthe context of CLEF2025 providing six tasks: (i) Task b on biomedicalsemantic question answering. (ii) Task Synergy on question answeringdeveloping biomedical topics. (iii) Task MultiClinSum on multilingualclinical summarization. (iv) Task BioNNE-L on nested named entity linkingin Russian and English. (v) Task ELCardioCC on clinical coding incardiology. (vi) Task GutBrainIE on gut-brain interplay information extraction.As BioASQ rewards the methods that outperform the state of the art in these shared tasks, it keeps pushing the research frontier towardsapproaches that will meet the need for efficient and precise accessto biomedical knowledge.

Присоединяйтесь к AIRI в соцсетях