Publication
The rapidly increasing number of biomedical publications presents a significant challenge for efficient knowledge discovery. To address this, we introduce an open-source, end-to-end framework designed to automatically extract and construct knowledge about specific diseases directly from unstructured text. To facilitate research in disease-related knowledge discovery, we create two annotated datasets focused on Rett syndrome (RS) and Alzheimer's disease (AD), enabling the identification of semantic relations between various biomedical entities. We perform extensive benchmarking to evaluate different approaches for representing relations and entities, providing insights into optimal modeling strategies for semantic relation detection and highlighting language models' competence in knowledge discovery. To gain a deeper understanding of the internal mechanisms of transformer models, we also conduct probing experiments, analyzing different layer representations and attention scores, to explore transformers' ability to capture semantic relations within the text. Both the code and the datasets will be publicly available, encouraging further research in biomedical knowledge discovery.