{"url":"/dataset/swde","name":"SWDE","full_name":"Structured Web Data Extraction","description_markdown":"This dataset is a real-world web page collection used for research on the automatic extraction of structured data (e.g., attribute-value pairs of entities) from the Web. We hope it could serve as a useful benchmark for evaluating and comparing different methods for structured web data extraction.\r\n\r\nSource: [Official](https://archive.codeplex.com/?p=swde)","description_withheld":null,"homepage":"https://archive.codeplex.com/?p=swde","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Attribute Extraction","url":"/task/attribute-extraction","datasets_with_task":"/datasets/task/attribute-extraction"}],"languages":[],"variants":["SWDE"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/attribute-extraction-on-swde","task":"Attribute Extraction","dataset_variant":"SWDE","rows":2,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"InstrucTE (zero-shot)","paper":"/paper/schema-driven-information-extraction-from","metrics":{"Avg F1":"95.7"},"code_links":[{"title":"bflashcp3f/schema-to-json","url":"https://github.com/bflashcp3f/schema-to-json"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/schema-driven-information-extraction-from","title":"Schema-Driven Information Extraction from Heterogeneous Tables","date":"2023-05-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dom-lm-learning-generalizable-representations","title":"DOM-LM: Learning Generalizable Representations for HTML Documents","date":"2022-01-25","rows_on_this_dataset":1,"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."}