AAbAAC: An Annotated Corpus for Autoimmunity Information Extraction

The AAbAAC (AutoAntibodies and Autoimmunity Annotated Corpus) has been released, consisting of 115 manually annotated abstracts from PubMed focused on entities related to autoimmune diseases and autoantibodies. The corpus was utilized to evaluate and fine-tune named entity recognition (NER) models, demonstrating improved performance in extracting specialized biomedical information. This resource highlights the importance of domain-specific annotated datasets for enhancing the capabilities of AI models in complex biomedical fields.