PubMedQA: A Dataset for Biomedical Research Question Answering

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.

PDF Abstract IJCNLP 2019 PDF IJCNLP 2019 Abstract

Datasets


Introduced in the Paper:

PubMedQA

Used in the Paper:

HotpotQA BioASQ

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering PubMedQA Human Performance (single annotator) Accuracy 78.0 # 7

Methods


No methods listed for this paper. Add relevant methods here