{"url":"/dataset/lener-br","name":"LeNER-Br","full_name":null,"description_markdown":"LeNER-Br is a dataset for named entity recognition (NER) in Brazilian Legal Text.","description_withheld":null,"homepage":"https://teodecampos.github.io/LeNER-Br/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/lener-br-a-dataset-for-named-entity","title":"LeNER-Br: a Dataset for Named Entity Recognition in Brazilian Legal Text","first_author":"Pedro H. Luz de Araujo","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Token Classification","url":"/task/token-classification","datasets_with_task":"/datasets/task/token-classification"}],"languages":[{"name":"Portuguese","url":"/datasets/language/portuguese"}],"variants":["LeNER-Br","lener_br","pierreguillou/lener_br_finetuning_language_model"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/peluz/lener_br","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/pierreguillou/lener_br_finetuning_language_model","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lener_br","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-on-lener-br","task":"Named Entity Recognition (NER)","dataset_variant":"LeNER-Br","rows":1,"metrics":["Micro F1 (Exact Span)","Micro F1 (Tokens)"],"first_row_in_archive_order":{"model":"LSTM-CRF","paper":"/paper/lener-br-a-dataset-for-named-entity","metrics":{"Micro F1 (Exact Span)":"0.8661","Micro F1 (Tokens)":"0.9253"},"code_links":[{"title":"peluz/lener-br","url":"https://github.com/peluz/lener-br"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/token-classification-on-lener-br","task":"Token Classification","dataset_variant":"lener_br","rows":0,"metrics":["Accuracy","F1","Loss","Precision","Recall"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/lener-br-a-dataset-for-named-entity","title":"LeNER-Br: a Dataset for Named Entity Recognition in Brazilian Legal Text","date":"2018-09-24","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."}