PubMedQA: A Dataset for Biomedical Research Question Answering

TL;DR

PubMedQA is a new biomedical QA dataset from PubMed abstracts designed to evaluate reasoning over research texts, with models achieving 68.1% accuracy, highlighting the challenge of biomedical question answering.

Contribution

It introduces the first biomedical QA dataset requiring reasoning over research texts, including a large set of artificially generated and expert-annotated instances.

Findings

Best model achieves 68.1% accuracy

Model performance is below human accuracy of 78%

The dataset enables research on biomedical reasoning

Abstract

We introduce PubMedQA, a novel biomedical question answering (QA) dataset collected from PubMed abstracts. 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-annotated, 61.2k unlabeled and 211.3k artificially generated QA instances. Each PubMedQA instance is composed of (1) a question which is either an existing research article title or derived from one, (2) a context which is the corresponding abstract without its conclusion, (3) a long answer, which is the conclusion of the abstract and, presumably, answers the research question, and (4) a yes/no/maybe answer which summarizes the conclusion. PubMedQA is the first QA dataset where reasoning over biomedical research texts, especially their quantitative contents, is required to answer the questions. Our best performing model, multi-phase fine-tuning of BioBERT with long answer bag-of-word statistics as additional supervision, achieves 68.1% accuracy, compared to single human performance of 78.0% accuracy and majority-baseline of 55.2% accuracy, leaving much room for improvement. PubMedQA is publicly available at https://pubmedqa.github.io.