{"url":"/dataset/gittables-semtab","name":"GitTables-SemTab","full_name":null,"description_markdown":"The GitTables-SemTab dataset is a subset of the [GitTables](https://paperswithcode.com/dataset/gittables) dataset and was created to be used during the [SemTab](http://www.cs.ox.ac.uk/isg/challenges/sem-tab/) challenge. The dataset consists of 1101 tables and is used to benchmark the Column Type Annotation (CTA) task. \r\n\r\nIts columns were annotated using semantic properties from DBpedia and semantic types and properties from Schema.org. The table below shows the number of annotated columns and number of classes used to annotate this dataset.\r\n\r\n|                | Columns | Classes |\r\n|----------------|-------|-------|\r\n| Column Type Annotation - Schema.org    |   721   |    59   |\r\n| Column Type Annotation  - DBpedia | 2,533  |   122   |","description_withheld":null,"homepage":"https://zenodo.org/record/5706316","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Column Type Annotation","url":"/task/column-type-annotation","datasets_with_task":"/datasets/task/column-type-annotation"}],"languages":[],"variants":["GitTables-SemTab","GitTables-SemTab-DBP","GitTables-SemTab-SCH"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/column-type-annotation-on-gittables-semtab","task":"Column Type Annotation","dataset_variant":"GitTables-SemTab-DBP","rows":3,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"KGCODE-Tab","paper":"/paper/kgcode-tab-results-for-semtab-2022","metrics":{"F1 (%)":"58.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/column-type-annotation-on-gittables-semtab-1","task":"Column Type Annotation","dataset_variant":"GitTables-SemTab-SCH","rows":2,"metrics":["F1 (%)"],"first_row_in_archive_order":{"model":"KGCODE-Tab","paper":"/paper/kgcode-tab-results-for-semtab-2022","metrics":{"F1 (%)":"69.3"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"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/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/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."}