{"url":"/dataset/eurlex57k","name":"EURLEX57K","full_name":null,"description_markdown":"EURLEX57K is a new publicly available legal LMTC dataset, dubbed EURLEX57K, containing 57k English EU legislative documents from the EUR-LEX portal, tagged with ∼4.3k labels (concepts) from the European Vocabulary (EUROVOC).\r\n\r\nSource: [Large-Scale Multi-Label Text Classification on EU Legislation](https://www.aclweb.org/anthology/P19-1636.pdf)","description_withheld":null,"homepage":"https://github.com/iliaschalkidis/lmtc-eurlex57k","introduced_date":"2019-06-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/large-scale-multi-label-text-classification-1","title":"Large-Scale Multi-Label Text Classification on EU Legislation","first_author":"Ilias Chalkidis","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","datasets_with_task":"/datasets/task/zero-shot-learning"},{"name":"Multi-Label Text Classification","url":"/task/multi-label-text-classification","datasets_with_task":"/datasets/task/multi-label-text-classification"},{"name":"Hierarchical Multi-label Classification","url":"/task/hierarchical-multi-label-classification","datasets_with_task":"/datasets/task/hierarchical-multi-label-classification"},{"name":"Multilabel Text Classification","url":"/task/multilabel-text-classification","datasets_with_task":"/datasets/task/multilabel-text-classification"}],"languages":[],"variants":["EURLEX57K"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/NLP-AUEB/eurlex","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jonathanli/eurlex","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/eurlex","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/iliaschalkidis/lmtc-eurlex57k","url":"https://github.com/iliaschalkidis/lmtc-eurlex57k","frameworks":["tf"]}],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/hierarchical-multi-label-classification-on-19","task":"Hierarchical Multi-label Classification","dataset_variant":"EURLEX57K","rows":4,"metrics":["Macro F1","Micro F1"],"first_row_in_archive_order":{"model":"HiDEC+HBM Loss","paper":"/paper/hierarchy-aware-biased-bound-margin-loss","metrics":{"Macro F1":"28.77±0.11","Micro F1":"76.48±0.12"},"code_links":[{"title":"whitepurple/HBM-loss-for-HTC","url":"https://github.com/whitepurple/HBM-loss-for-HTC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/hierarchy-aware-biased-bound-margin-loss","title":"Hierarchy-aware Biased Bound Margin Loss Function for Hierarchical Text Classification","date":"2024-08-13","rows_on_this_dataset":4,"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."}