DiSCQ

홈페이지 · 논문 4편

DiSCQ is a newly curated question dataset composed of 2,000+ questions paired with the snippets of text (triggers) that prompted each question. The questions are generated by medical experts from 100+ MIMIC-III discharge summaries. This dataset is released to facilitate further research into realistic clinical Question Answering (QA) and Question Generation (QG). Source: Learning to Ask Like a Physician Image Source: https://arxiv.org/pdf/2206.02696.pdf