BioRED is a first-of-its-kind biomedical relation extraction dataset with multiple entity types (e.g. gene/protein, disease, chemical) and relation pairs (e.g. gene–disease; chemical–chemical) at the document level, on a set of600 PubMed abstracts. Furthermore, BioRED label each relation as describing either a novel finding or previously known background knowledge, enabling automated algorithms to differentiate between novel and background information.
Variants: BioRED
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Relation Extraction | PubMedBERT | BioRED: A Rich Biomedical Relation … | 2022-04-08 |
| Named Entity Recognition (NER) | PubMedBERT-CRF | BioRED: A Rich Biomedical Relation … | 2022-04-08 |
| Named Entity Recognition (NER) | BioBERT-CRF | BioRED: A Rich Biomedical Relation … | 2022-04-08 |
| Named Entity Recognition (NER) | BiLSTM-CRF | BioRED: A Rich Biomedical Relation … | 2022-04-08 |
| Relation Extraction | BERT-GT | BERT-GT: Cross-sentence n-ary relation extraction … | 2021-01-11 |
Recent papers with results on this dataset: