{"url":"/dataset/nerel-bio","name":"NEREL-BIO","full_name":null,"description_markdown":"**NEREL-BIO** is an annotation scheme and corpus of PubMed abstracts in Russian and English. It contains annotations for 700+ Russian and 100+ English abstracts. All English PubMed annotations have corresponding Russian counterparts. NEREL-BIO comprises the following specific features: annotation of nested named entities, it can be used as a benchmark for cross-domain (NEREL -> NEREL-BIO) and cross-language (English -> Russian) transfer.\r\n\r\nSource: [NEREL-BIO: A Dataset of Biomedical Abstracts Annotated with Nested Named Entities](https://arxiv.org/pdf/2210.11913v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.11913v1.pdf](https://arxiv.org/pdf/2210.11913v1.pdf)","description_withheld":null,"homepage":"https://github.com/nerel-ds/NEREL-BIO","introduced_date":"2022-10-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/nerel-bio-a-dataset-of-biomedical-abstracts","title":"NEREL-BIO: A Dataset of Biomedical Abstracts Annotated with Nested Named Entities","first_author":"Natalia Loukachevitch","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Machine Reading Comprehension","url":"/task/machine-reading-comprehension","datasets_with_task":"/datasets/task/machine-reading-comprehension"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Russian","url":"/datasets/language/russian"}],"variants":["NEREL-BIO"],"data_loaders":[],"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."}