PubMedQA

TextsCustomIntroduced 2019-09-13

The task of PubMedQA is to answer research questions with yes/no/maybe (e.g.: Do preoperative statins reduce atrial fibrillation after coronary artery bypass grafting?) using the corresponding abstracts.

PubMedQA has 1k expert labeled, 61.2k unlabeled and 211.3k artificially generated QA instances.

Source: PubMedQA Image Source: https://arxiv.org/pdf/1909.06146v1.pdf

Benchmarks

Few-Shot Learning/Accuracy Meta-Learning/Accuracy Question Answering/Accuracy Retrieval/Accuracy (Top-1)

Related Benchmarks

PubMedQA corpus with metadata/Inductive knowledge graph completion/ANS-EM PubMedQA corpus with metadata/Knowledge Graph Completion/ANS-EM PubMedQA corpus with metadata/Knowledge Graphs/ANS-EM PubMedQA corpus with metadata/Large Language Model/ANS-EM PubMedQA corpus with metadata/Retrieval/Accuracy (Top-1)