Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
The vast amount of COVID-19 research literature has made it difficult for medical experts, clinical scientists, and researchers to keep up with the latest research findings. We present two datasets for COVID-19 in this work: (1) first, we create a dataset from the up-to-date scientific publications on COVID-19, and (2) second, we build a gold-standard dataset of question-answering pairs annotated by volunteer biomedical experts on COVID-19 related scientific articles. We develop a question-answering (QA) pipeline that uses the first dataset to provide answers related to COVID-19 questions; we fine-tune MPNet (a Transformer model) on our gold-standard dataset and use it in the QA pipeline to enhance its reading capability. We also use this gold-standard dataset to evaluate the QA pipeline. The proposed MPNet version on the gold-standard dataset outperformed previous datasets and models, achieving an Exact Match/Fl score of 69.72/78.50 %, respectively