MRC-based Nested Medical NER with Co-prediction and Adaptive Pre-training

arXiv:2403.15800v1 Announce Type: new
Abstract: In medical information extraction, medical Named Entity Recognition (NER) is indispensable, playing a crucial role in developing medical knowledge graphs, enhancing medical question-answering systems, and analyzing electronic medical records. The challenge in medical NER arises from the complex nested structures and sophisticated medical terminologies, distinguishing it from its counterparts in traditional domains. In response to these complexities, we propose a medical NER model based on Machine Reading Comprehension (MRC), which uses a task-adaptive pre-training strategy …

abstract arxiv challenge cs.cl electronic extraction graphs information information extraction knowledge knowledge graphs medical medical records ner playing prediction pre-training question recognition records role systems training type