{"url":"/dataset/chilean-waiting-list-corpus","name":"Chilean Waiting List","full_name":null,"description_markdown":"The Chilean Waiting List corpus comprises de-identified referrals from the waiting list in Chilean public hospitals. A subset of 10,000 referrals (including medical\r\nand dental notes) was manually annotated with ten entity types with clinical relevance, keeping 1,000 annotations for a future shared task. A trained medical doctor or dentist annotated these referrals and then, together with three other researchers, consolidated each of the annotations. The annotated corpus has more than 48% of entities embedded in\r\nother entities or containing another. This corpus can be a useful resource to build new models for Nested Named Entity Recognition (NER). This work constitutes the first\r\nannotated corpus using clinical narratives from Chile and one of the few in Spanish.\r\n\r\nHugging Face datasets: https://huggingface.co/plncmm. After predicting over each entity type, merge the prediction to obtain your final micro f1-score. This is for a fair comparison with actual state-of-the-art models.","description_withheld":null,"homepage":"https://zenodo.org/record/7555181#.Y87MNexBzzc","introduced_date":"2023-01-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/automatic-extraction-of-nested-entities-in","title":"Automatic Extraction of Nested Entities in Clinical Referrals in Spanish","first_author":"Pablo Báez","url":null},"license":{"name":"Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.","url":"http://creativecommons.org/licenses/by-nc-sa/4.0/."},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Nested Named Entity Recognition","url":"/task/nested-named-entity-recognition","datasets_with_task":"/datasets/task/nested-named-entity-recognition"}],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"}],"variants":["Chilean Waiting List"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/nested-named-entity-recognition-on-chilean","task":"Nested Named Entity Recognition","dataset_variant":"Chilean Waiting List","rows":1,"metrics":["Micro F1 (Exact Span)"],"first_row_in_archive_order":{"model":"Multiple LSTM-CRF","paper":"/paper/simple-yet-powerful-an-overlooked-1","metrics":{"Micro F1 (Exact Span)":"80.5"},"code_links":[{"title":"matirojasg/nestednereval","url":"https://github.com/matirojasg/nestednereval"},{"title":"matirojasg/nested-ner-mlc","url":"https://github.com/matirojasg/nested-ner-mlc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/simple-yet-powerful-an-overlooked-1","title":"Simple Yet Powerful: An Overlooked Architecture for Nested Named Entity Recognition","date":"2022-10-01","rows_on_this_dataset":1,"code_links":2,"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."}