PubMedQA: A Dataset for Biomedical Research Question Answering

Explore this paper's citation graph

Summary

The 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.

Type
article
Published
2019-09-01
Cited by
1,872
References
23
Access
Open access

Keywords

Question answering, Computer science, Natural language processing, Natural (archaeology), Natural language

References

Cited by

Related papers