{"url":"/dataset/2010-i2b2-va","name":"2010 i2b2/VA","full_name":"2010 i2b2/VA","description_markdown":"**2010 i2b2/VA** is a biomedical dataset for relation classification and entity typing.","description_withheld":null,"homepage":"https://www.i2b2.org/NLP/Relations/","introduced_date":null,"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":"FG-1-PG-1","url":"/task/fg-1-pg-1","datasets_with_task":"/datasets/task/fg-1-pg-1"},{"name":"Medical Named Entity Recognition","url":"/task/medical-named-entity-recognition","datasets_with_task":"/datasets/task/medical-named-entity-recognition"},{"name":"Clinical Concept Extraction","url":"/task/clinical-concept-extraction","datasets_with_task":"/datasets/task/clinical-concept-extraction"},{"name":"Clinical Assertion Status Detection","url":"/task/clinical-assertion-status-detection","datasets_with_task":"/datasets/task/clinical-assertion-status-detection"}],"languages":[],"variants":["2010 i2b2/VA"],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/clinical-concept-extraction-on-2010-i2b2va","task":"Clinical Concept Extraction","dataset_variant":"2010 i2b2/VA","rows":5,"metrics":["Exact Span F1"],"first_row_in_archive_order":{"model":"BERTlarge (MIMIC)","paper":"/paper/enhancing-clinical-concept-extraction-with","metrics":{"Exact Span F1":"90.25"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/clinical-assertion-status-detection-on-2010","task":"Clinical Assertion Status Detection","dataset_variant":"2010 i2b2/VA","rows":1,"metrics":["Micro F1"],"first_row_in_archive_order":{"model":"BiLSTM (SparkNLP)","paper":"/paper/improving-clinical-document-understanding-on","metrics":{"Micro F1":"0.939"},"code_links":[{"title":"JohnSnowLabs/spark-nlp-workshop","url":"https://github.com/JohnSnowLabs/spark-nlp-workshop/tree/master/tutorials/Certification_Trainings/Healthcare"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fg-1-pg-1-on-2010-i2b2-va","task":"FG-1-PG-1","dataset_variant":"2010 i2b2/VA","rows":1,"metrics":["F1 (macro)","F1 (micro)"],"first_row_in_archive_order":{"model":"CFNER","paper":"/paper/distilling-causal-effect-from-miscellaneous","metrics":{"F1 (macro)":"0.3626","F1 (micro)":"0.6273"},"code_links":[{"title":"zzz47zzz/CFNER","url":"https://github.com/zzz47zzz/CFNER"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/relation-extraction-on-2010-i2b2-va-1","task":"Relation Extraction","dataset_variant":"2010 i2b2/VA","rows":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"Spark NLP","paper":"/paper/deeper-clinical-document-understanding-using","metrics":{"Macro F1":"69.1"},"code_links":[{"title":"JohnSnowLabs/spark-nlp-workshop","url":"https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/Certification_Trainings/Healthcare/10.3.Clinical_RE_SparkNLP_Paper_Reproduce.ipynb"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/distilling-causal-effect-from-miscellaneous","title":"Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition","date":"2022-10-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deeper-clinical-document-understanding-using","title":"Deeper Clinical Document Understanding Using Relation Extraction","date":"2021-12-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-clinical-document-understanding-on","title":"Improving Clinical Document Understanding on COVID-19 Research with Spark NLP","date":"2020-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/characterbert-reconciling-elmo-and-bert-for","title":"CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters","date":"2020-10-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cost-effective-selection-of-pretraining-data","title":"Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media","date":"2020-10-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/embedding-strategies-for-specialized-domains","title":"Embedding Strategies for Specialized Domains: Application to Clinical Entity Recognition","date":"2019-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/enhancing-clinical-concept-extraction-with","title":"Enhancing Clinical Concept Extraction with Contextual Embeddings","date":"2019-02-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/machine-learned-solutions-for-three-stages-of","title":"Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010","date":"2011-05-12","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":0,"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."}