{"url":"/dataset/coneco","name":"CoNECo","full_name":"Complex Named Entity Corpus","description_markdown":"Complex Named Entity Corpus (CoNECo) is an annotated corpus for NER and NEN of protein-containing complexes. CoNECo comprises 1,621 documents with 2,052 entities, 1,976 of which are normalized to Gene Ontology. We divided the corpus into training, development, and test sets.","description_withheld":null,"homepage":"https://zenodo.org/records/11263147","introduced_date":"2024-05-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/coneco-a-corpus-for-named-entity-recognition","title":"CoNECo: A corpus for named entity recognition and normalization of protein complexes","first_author":"Katerina Nastou","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition","url":"/task/named-entity-recognition-1","datasets_with_task":"/datasets/task/named-entity-recognition-1"},{"name":"Medical Concept Normalization","url":"/task/medical-concept-normalization","datasets_with_task":"/datasets/task/medical-concept-normalization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CoNECo"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/bigbio/coneco","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}