{"url":"/dataset/sv-ident","name":"SV-Ident","full_name":"Survey Variable Identification","description_markdown":"SV-Ident comprises 4,248 sentences from social science publications in English and German. The data is the official data for the Shared Task: “Survey Variable Identification in Social Science Publications” (SV-Ident) 2022. Sentences are labeled with variables that are mentioned either explicitly or implicitly. \r\n\r\nThe dataset supports the following tasks:\r\n\r\n- Variable Detection: identifying whether a sentence contains a variable mention or not.\r\n\r\n- Variable Disambiguation: identifying which variable from a given vocabulary is mentioned in a sentence.","description_withheld":null,"homepage":"https://vadis-project.github.io/sv-ident-sdp2022/","introduced_date":"2022-09-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/overview-of-the-sv-ident-2022-shared-task-on","title":"Overview of the SV-Ident 2022 Shared Task on Survey Variable Identification in Social Science Publications","first_author":"Tornike Tsereteli","url":null},"license":{"name":"https://www.gesis.org/en/ssoar/home/information/grant-of-licences","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Multi-Label Text Classification","url":"/task/multi-label-text-classification","datasets_with_task":"/datasets/task/multi-label-text-classification"},{"name":"Paraphrase Identification","url":"/task/paraphrase-identification","datasets_with_task":"/datasets/task/paraphrase-identification"},{"name":"Semantic Similarity","url":"/task/semantic-similarity","datasets_with_task":"/datasets/task/semantic-similarity"},{"name":"Cross-Lingual Paraphrase Identification","url":"/task/cross-lingual-paraphrase-identification","datasets_with_task":"/datasets/task/cross-lingual-paraphrase-identification"},{"name":"Variable Detection","url":"/task/variable-detection","datasets_with_task":"/datasets/task/variable-detection"},{"name":"Variable Disambiguation","url":"/task/variable-disambiguation","datasets_with_task":"/datasets/task/variable-disambiguation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"German","url":"/datasets/language/german"}],"variants":["SV-Ident"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/vadis/sv-ident","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://github.com/huggingface/datasets","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/variable-disambiguation-on-sv-ident","task":"Variable Disambiguation","dataset_variant":"SV-Ident","rows":4,"metrics":["mAP@10"],"first_row_in_archive_order":{"model":"sentence-transformers/distiluse-base-multilingual-cased-v1","paper":"/paper/overview-of-the-sv-ident-2022-shared-task-on","metrics":{"mAP@10":"18.93"},"code_links":[{"title":"vadis-project/sv-ident","url":"https://github.com/vadis-project/sv-ident"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/variable-detection-on-sv-ident","task":"Variable Detection","dataset_variant":"SV-Ident","rows":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"SsciBERT","paper":"/paper/overview-of-the-sv-ident-2022-shared-task-on","metrics":{"F1":"66.1"},"code_links":[{"title":"vadis-project/sv-ident","url":"https://github.com/vadis-project/sv-ident"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/overview-of-the-sv-ident-2022-shared-task-on","title":"Overview of the SV-Ident 2022 Shared Task on Survey Variable Identification in Social Science Publications","date":"2022-09-19","rows_on_this_dataset":6,"code_links":1,"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."}