BioASQ at CLEF2023: The Eleventh Edition of the Large-Scale Biomedical Semantic Indexing and Question Answering Challenge

Abstract

The large-scale biomedical semantic indexing and question-answering challenge (BioASQ) aims at the continuous advancement of methods and tools to meet the need of biomedical researchers and practitioners for efficient and precise access to the ever-increasing resources of their domain. With this purpose, during the last ten years a series of annual challenges have been organized with specific shared tasks on large-scale biomedical semantic indexing and question answering. Benchmark datasets have been concomitantly provided in alignment with the real needs of biomedical experts. BioASQ provides a unique common testbed where different teams around the world can investigate and compare new approaches for identifying and accessing biomedical knowledge. The eleventh version of the BioASQ Challenge will be held as an evaluation Lab within CLEF2023. In this version, three shared tasks will be presented: (i) the automated retrieval of relevant material for biomedical questions, and the generation of comprehensible answers. (ii) the synergistic retrieval of relevant material and generation of answers for open biomedical questions about developing topics, in collaboration with the experts posing the questions. (iii) the automated indexing of unlabelled clinical procedures-specific medical documents, primarily clinical case reports written in Spanish, with biomedical concepts and the extraction of human-interpretable evidence. As BioASQ rewards the methods that outperform the state of the art in these shared tasks, it pushes the research frontier towards approaches that accelerate access to biomedical knowledge.