{"url":"/dataset/biodivtab","name":"BiodivTab","full_name":null,"description_markdown":"The BioDiv dataset includes manually labeled tables for CTA and CEA from the biodiversity domain.","description_withheld":null,"homepage":"https://github.com/fusion-jena/BiodivTab","introduced_date":"2023-01-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/biodivtab-semantic-table-annotation-benchmark","title":"BiodivTab: Semantic Table Annotation Benchmark Construction, Analysis, and New Additions","first_author":"Nora Abdelmageed","url":null},"license":{"name":"CC BY 4.0","url":null},"modalities":[],"tasks":[{"name":"Column Type Annotation","url":"/task/column-type-annotation","datasets_with_task":"/datasets/task/column-type-annotation"},{"name":"Cell Entity Annotation","url":"/task/cell-entity-annotation","datasets_with_task":"/datasets/task/cell-entity-annotation"}],"languages":[],"variants":["BiodivTab"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/column-type-annotation-on-biodivtab","task":"Column Type Annotation","dataset_variant":"BiodivTab","rows":6,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"KGCODE-Tab","paper":"/paper/kgcode-tab-results-for-semtab-2022","metrics":{"F1 (%)":"86.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/cell-entity-annotation-on-biodivtab","task":"Cell Entity Annotation","dataset_variant":"BiodivTab","rows":5,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"KGCODE-Tab","paper":"/paper/kgcode-tab-results-for-semtab-2022","metrics":{"F1 (%)":"91.1"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/towards-an-approach-based-on-knowledge-graph","title":"Towards an Approach based on Knowledge Graph Refinement for Tabular Data to Knowledge Graph Matching","date":"2022-10-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/kgcode-tab-results-for-semtab-2022","title":"KGCODE-Tab Results for SemTab 2022","date":"2022-10-25","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/magic-mining-an-augmented-graph-using-ink","title":"MAGIC: Mining an Augmented Graph using INK, starting from a CSV","date":"2021-10-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/kepler-asi-at-semtab-2021","title":"Kepler-aSI at SemTab 2021","date":"2021-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/jentab-meets-semtab-2021-s-new-challenges","title":"JenTab Meets SemTab 2021's New Challenges","date":"2021-10-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/dagobah-table-and-graph-contexts-for","title":"DAGOBAH: Table and Graph Contexts for Efficient Semantic Annotation of Tabular Data","date":"2021-10-01","rows_on_this_dataset":2,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"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."}