{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:00:43Z","timestamp":1776182443680,"version":"3.50.1"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2023,4,2]],"date-time":"2023-04-02T00:00:00Z","timestamp":1680393600000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"publisher","award":["20-11-20166"],"award-info":[{"award-number":["20-11-20166"]}],"id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,4,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>This article describes NEREL-BIO\u2014an annotation scheme and corpus of PubMed abstracts in Russian and smaller number of abstracts in English. NEREL-BIO extends the general domain dataset NEREL by introducing domain-specific entity types. NEREL-BIO annotation scheme covers both general and biomedical domains making it suitable for domain transfer experiments. NEREL-BIO provides annotation for nested named entities as an extension of the scheme employed for NEREL. Nested named entities may cross entity boundaries to connect to shorter entities nested within longer entities, making them harder to detect.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>NEREL-BIO contains annotations for 700+ Russian and 100+ English abstracts. All English PubMed annotations have corresponding Russian counterparts. Thus, NEREL-BIO comprises the following specific features: annotation of nested named entities, it can be used as a benchmark for cross-domain (NEREL \u2192 NEREL-BIO) and cross-language (English \u2192 Russian) transfer. We experiment with both transformer-based sequence models and machine reading comprehension models and report their results.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The dataset and annotation guidelines are freely available at https:\/\/github.com\/nerel-ds\/NEREL-BIO.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad161","type":"journal-article","created":{"date-parts":[[2023,4,2]],"date-time":"2023-04-02T16:10:53Z","timestamp":1680451853000},"source":"Crossref","is-referenced-by-count":21,"title":["NEREL-BIO: a dataset of biomedical abstracts annotated with nested named entities"],"prefix":"10.1093","volume":"39","author":[{"given":"Natalia","family":"Loukachevitch","sequence":"first","affiliation":[{"name":"Lomonosov Moscow State University , Moscow 19899, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suresh","family":"Manandhar","sequence":"additional","affiliation":[{"name":"Madan Bhandari University of Science and Technology , Chitlang 44600, Nepal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elina","family":"Baral","sequence":"additional","affiliation":[{"name":"Madan Bhandari University of Science and Technology , Chitlang 44600, Nepal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor","family":"Rozhkov","sequence":"additional","affiliation":[{"name":"Lomonosov Moscow State University , Moscow 19899, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Braslavski","sequence":"additional","affiliation":[{"name":"Ural Federal University , Yekaterinburg 620002, Russia"},{"name":"HSE University , Moscow 101000, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Ivanov","sequence":"additional","affiliation":[{"name":"Innopolis University , Innopolis 420500, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4333-7888","authenticated-orcid":false,"given":"Tatiana","family":"Batura","sequence":"additional","affiliation":[{"name":"A.P. Ershov Institute of Informatics Systems , Novosibirsk 630090, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7936-0284","authenticated-orcid":false,"given":"Elena","family":"Tutubalina","sequence":"additional","affiliation":[{"name":"HSE University , Moscow 101000, Russia"},{"name":"Artificial Intelligence Research Institute , Moscow 105064, Russia"},{"name":"Sber AI , Moscow 121170, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,4,2]]},"reference":[{"key":"2023042602470807400_btad161-B1","author":"Artemova","year":"2022"},{"key":"2023042602470807400_btad161-B2","first-page":"660","author":"Bawden","year":"2020"},{"key":"2023042602470807400_btad161-B3","first-page":"383","volume-title":"Lect Notes Comput Sci","author":"Blinov","year":"2022"},{"key":"2023042602470807400_btad161-B4","doi-asserted-by":"crossref","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"The unified medical language system (UMLS): integrating biomedical terminology","volume":"32","author":"Bodenreider","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2023042602470807400_btad161-B5","first-page":"1473","author":"Buaphet","year":"2022"},{"key":"2023042602470807400_btad161-B6","first-page":"1","article-title":"A clinical trials corpus annotated with UMLS entities to enhance the access to evidence-based medicine","volume":"21","author":"Campillos-Llanos","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"2023042602470807400_btad161-B7","first-page":"11","author":"Checco","year":"2017"},{"key":"2023042602470807400_btad161-B8","first-page":"4171","author":"Devlin","year":"2019"},{"key":"2023042602470807400_btad161-B9","author":"Fries","year":"2022"},{"key":"2023042602470807400_btad161-B10","first-page":"15","author":"Gurulingappa","year":"2010"},{"key":"2023042602470807400_btad161-B11","author":"Katiyar","year":"2018"},{"key":"2023042602470807400_btad161-B12","doi-asserted-by":"crossref","first-page":"31513","DOI":"10.1109\/ACCESS.2022.3157854","article-title":"How do your biomedical named entity recognition models generalize to novel entities?","volume":"10","author":"Kim","year":"2022","journal-title":"IEEE Access"},{"key":"2023042602470807400_btad161-B13","doi-asserted-by":"crossref","first-page":"i180","DOI":"10.1093\/bioinformatics\/btg1023","article-title":"Genia corpus\u2014a semantically annotated corpus for bio-textmining","volume":"19","author":"Kim","year":"2003","journal-title":"Bioinformatics"},{"key":"2023042602470807400_btad161-B14","first-page":"411","article-title":"Reliability in content analysis: some common misconceptions and recommendations","volume":"30","author":"Krippendorff","year":"2004","journal-title":"Hum Commun Res"},{"key":"2023042602470807400_btad161-B15","first-page":"333","volume-title":"Komp'juternaja Lingvistika i Intellektual'nye Tehnologii","author":"Kuratov","year":"2019"},{"key":"2023042602470807400_btad161-B16","first-page":"82","author":"Leaman","year":"2009"},{"key":"2023042602470807400_btad161-B17","first-page":"5849","author":"Li","year":"2020"},{"key":"2023042602470807400_btad161-B18","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/j.neucom.2022.07.012","article-title":"Handling negative samples problems in span-based nested named entity recognition","volume":"505","author":"Liu","year":"2022","journal-title":"Neurocomputing"},{"key":"2023042602470807400_btad161-B19","first-page":"876","author":"Loukachevitch","year":"2021"},{"key":"2023042602470807400_btad161-B20","first-page":"4458","author":"Loukachevitch","year":"2022"},{"key":"2023042602470807400_btad161-B21","first-page":"281","author":"Miftahutdinov","year":"2020"},{"key":"2023042602470807400_btad161-B22","author":"Mohan","year":"2018"},{"key":"2023042602470807400_btad161-B23","first-page":"239","author":"Nesterov","year":"2022"},{"key":"2023042602470807400_btad161-B24","author":"N\u00e9v\u00e9ol","year":"2014"},{"key":"2023042602470807400_btad161-B25","volume-title":"NIH UMLS Statistics","author":"NIH UMLS","year":"2022"},{"key":"2023042602470807400_btad161-B26","first-page":"6649","author":"Plank","year":"2020"},{"key":"2023042602470807400_btad161-B27","first-page":"5176","author":"Ringland","year":"2019"},{"key":"2023042602470807400_btad161-B28","author":"Rozhkov","year":"2022"},{"key":"2023042602470807400_btad161-B29","first-page":"160","article-title":"Survey of agreement between raters for nominal data using Krippendorff\u2019s alpha","volume":"10","author":"Shabankhani","year":"2020","journal-title":"Arch Pharma Pract"},{"key":"2023042602470807400_btad161-B30","first-page":"605","article-title":"Nested named entity recognition via second-best sequence learning and decoding","volume":"8","author":"Shibuya","year":"2020","journal-title":"Trans Assoc Comput Ling"},{"key":"2023042602470807400_btad161-B31","first-page":"102","author":"Stenetorp","year":"2012"},{"key":"2023042602470807400_btad161-B32","first-page":"6710","author":"Tutubalina","year":"2020"},{"key":"2023042602470807400_btad161-B33","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1093\/bioinformatics\/btaa675","article-title":"The Russian drug reaction corpus and neural models for drug reactions and effectiveness detection in user reviews","volume":"37","author":"Tutubalina","year":"2021","journal-title":"Bioinformatics"},{"key":"2023042602470807400_btad161-B34","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1016\/j.jbi.2012.04.004","article-title":"The EU-ADR corpus: annotated drugs, diseases, targets, and their relationships","volume":"45","author":"Van Mulligen","year":"2012","journal-title":"J Biomed Inform"},{"key":"2023042602470807400_btad161-B35","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baw032","article-title":"Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task","volume":"2016","author":"Wei","year":"2016","journal-title":"Database"},{"key":"2023042602470807400_btad161-B36","author":"Zhou"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad161\/49726688\/btad161.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/4\/btad161\/50097748\/btad161.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/4\/btad161\/50097748\/btad161.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T02:47:28Z","timestamp":1682477248000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad161\/7099619"}},"subtitle":[],"editor":[{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,4,1]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad161","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,4,1]]},"published":{"date-parts":[[2023,4,1]]},"article-number":"btad161"}}