BioCreative V CDR Task Corpus
The BioCreative V CDR task corpus is manually annotated for chemicals, diseases and chemical-induced disease (CID) relations. It contains the titles and abstracts of 1500 PubMed articles and is split into equally sized train, validation and test sets. It is common to first tune a model on the validation set and then train on the combination of the train and validation sets before evaluating on the test set. It is also common to filter negative relations with disease entities that are hypernyms of a corresponding true relations disease entity within the same abstract (see Appendix C of this paper for details).
Variants: CDR
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Relation Extraction | DRE-MIR-SciBERT | A Masked Image Reconstruction Network … | 2022-04-21 |
| Relation Extraction | seq2rel (entity hinting) | A sequence-to-sequence approach for document-level … | 2022-04-03 |
| Relation Extraction | Dense-CCNet-SciBERTbase | A Densely Connected Criss-Cross Attention … | 2022-03-26 |
| Relation Extraction | CGM2IR-SciBERTbase | Document-level Relation Extraction with Context … | 2022-01-13 |
| Relation Extraction | SAISORE+CR+ET-SciBERT | SAIS: Supervising and Augmenting Intermediate … | 2021-09-24 |
| Relation Extraction | DocuNet-SciBERTbase | Document-level Relation Extraction as Semantic … | 2021-06-07 |
| Relation Extraction | SSANBiaffine | Entity Structure Within and Throughout: … | 2021-02-20 |
| Relation Extraction | SciBERT-ATLOPBASE | Document-Level Relation Extraction with Adaptive … | 2020-10-21 |
| Relation Extraction | LSR w/o MDP Nodes | Reasoning with Latent Structure Refinement … | 2020-05-13 |
Recent papers with results on this dataset: