BIOMRC: A Dataset for Biomedical Machine Reading Comprehension
This work provides a cleaner dataset for biomedical MRC, which is incremental but addresses noise issues for researchers in biomedical NLP.
The authors introduced BIOMRC, a large-scale cloze-style biomedical machine reading comprehension dataset designed to be less noisy than the previous BIOREAD dataset, and their best BERT-based model outperformed other methods, sometimes matching or surpassing biomedical expert accuracy.
We introduce BIOMRC, a large-scale cloze-style biomedical MRC dataset. Care was taken to reduce noise, compared to the previous BIOREAD dataset of Pappas et al. (2018). Experiments show that simple heuristics do not perform well on the new dataset, and that two neural MRC models that had been tested on BIOREAD perform much better on BIOMRC, indicating that the new dataset is indeed less noisy or at least that its task is more feasible. Non-expert human performance is also higher on the new dataset compared to BIOREAD, and biomedical experts perform even better. We also introduce a new BERT-based MRC model, the best version of which substantially outperforms all other methods tested, reaching or surpassing the accuracy of biomedical experts in some experiments. We make the new dataset available in three different sizes, also releasing our code, and providing a leaderboard.