{"url":"/dataset/cdr","name":"CDR","full_name":"BioCreative V CDR Task Corpus","description_markdown":"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](https://api.semanticscholar.org/CorpusID:247939302) for details).","description_withheld":null,"homepage":"https://biocreative.bioinformatics.udel.edu/tasks/biocreative-v/track-3-cdr/","introduced_date":"2016-08-05","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"Joint Entity and Relation Extraction","url":"/task/joint-entity-and-relation-extraction","datasets_with_task":"/datasets/task/joint-entity-and-relation-extraction"},{"name":"Reflection Removal","url":"/task/reflection-removal","datasets_with_task":"/datasets/task/reflection-removal"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CDR"],"data_loaders":[],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/relation-extraction-on-cdr","task":"Relation Extraction","dataset_variant":"CDR","rows":10,"metrics":["F1"],"first_row_in_archive_order":{"model":"SAISORE+CR+ET-SciBERT","paper":"/paper/sais-supervising-and-augmenting-intermediate","metrics":{"F1":"79"},"code_links":[{"title":"xiaoyuxin1002/sais","url":"https://github.com/xiaoyuxin1002/sais"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-cdr","task":"Joint Entity and Relation Extraction","dataset_variant":"CDR","rows":1,"metrics":["Relation F1"],"first_row_in_archive_order":{"model":"seq2rel","paper":"/paper/a-sequence-to-sequence-approach-for-document","metrics":{"Relation F1":"40.2"},"code_links":[{"title":"johngiorgi/seq2rel","url":"https://github.com/johngiorgi/seq2rel"},{"title":"JohnGiorgi/seq2rel-ds","url":"https://github.com/JohnGiorgi/seq2rel-ds"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/a-masked-image-reconstruction-network-for","title":"A Masked Image Reconstruction Network for Document-level Relation Extraction","date":"2022-04-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-sequence-to-sequence-approach-for-document","title":"A sequence-to-sequence approach for document-level relation extraction","date":"2022-04-03","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/a-densely-connected-criss-cross-attention","title":"A Densely Connected Criss-Cross Attention Network for Document-level Relation Extraction","date":"2022-03-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/document-level-relation-extraction-with-2","title":"Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoning","date":"2022-01-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/enhancing-biomedical-relation-extraction-with","title":"Enhancing Biomedical Relation Extraction with Transformer Models using Shortest Dependency Path Features and Triplet Information","date":"2021-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sais-supervising-and-augmenting-intermediate","title":"SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction","date":"2021-09-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/document-level-relation-extraction-as","title":"Document-level Relation Extraction as Semantic Segmentation","date":"2021-06-07","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/entity-structure-within-and-throughout","title":"Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction","date":"2021-02-20","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/document-level-relation-extraction-with","title":"Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling","date":"2020-10-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reasoning-with-latent-structure-refinement","title":"Reasoning with Latent Structure Refinement for Document-Level Relation Extraction","date":"2020-05-13","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":9,"samples_ran":7,"samples_unverified":2,"pointer_only_for_licence":8,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}