{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T22:00:54Z","timestamp":1785016854844,"version":"3.55.0"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Mention-agnostic biomedical concept recognition (MA-BCR) requires inferring ontology concepts directly from passages, without relying on explicit mention spans. Prior work has mainly focused on generative and classification-based approaches. Ranking-based methods typically use a retrieve-rerank pipeline, and this paradigm has not been systematically studied for MA-BCR. Consequently, it remains unclear how ranking-based approaches compare with existing paradigms and what types of supervision are most beneficial for ranker training under limited annotation settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Through a systematic comparison of ranking-, generative-, and classification-based paradigms, we show that a two-stage retrieve-rerank architecture is the most robust and scalable backbone for MA-BCR. Building on this finding, we propose ENR, an error-aware negative-enhanced ranking framework that augments training with false positives collected from heterogeneous recognizers, improving reranking performance without increasing inference-time cost. Experiments on MM-HPO and MM-GO (two datasets derived from MedMentions-ST21pv) demonstrate that ENR substantially outperforms prior approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The code and data underlying this article are available in Github at https:\/\/github.com\/sl-633\/enr-recognizer or in Zenodo at https:\/\/doi.org\/10.5281\/zenodo.20730803.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag495","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T13:21:23Z","timestamp":1783084883000},"source":"Crossref","is-referenced-by-count":0,"title":["Biomedical concept recognition with error-aware negative-enhanced ranking framework"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4370-4737","authenticated-orcid":false,"given":"Shanshan","family":"Liu","sequence":"first","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project , Nihonbashi 1-chome Mitsui Building, 15th floor, 1-4-1 Nihonbashi, Chuo-ku , Tokyo, 103-0027,","place":["Japan"]},{"name":"Graduate School of Science and Technology, University of Tsukuba , 1-1-1 Tennodai , Tsukuba, Ibaraki, 305-8577,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5851-7681","authenticated-orcid":false,"given":"Noriki","family":"Nishida","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project , Nihonbashi 1-chome Mitsui Building, 15th floor, 1-4-1 Nihonbashi, Chuo-ku , Tokyo, 103-0027,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5161-0544","authenticated-orcid":false,"given":"Fei","family":"Cheng","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University , S212, Research Bldg. No.9, Yoshida Main Campus, Yoshida-honmachi, Sakyo-ku , Kyoto, 606-8501,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takehito","family":"Utsuro","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Information and Systems, University of Tsukuba , 1-1-1 Tennodai , Tsukuba, 305-8573,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4946-9574","authenticated-orcid":false,"given":"Yuji","family":"Matsumoto","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project , Nihonbashi 1-chome Mitsui Building, 15th floor, 1-4-1 Nihonbashi, Chuo-ku , Tokyo, 103-0027,","place":["Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"key":"2026072517363494100_btag495-B1","author":"De Cao"},{"key":"2026072517363494100_btag495-B2","doi-asserted-by":"publisher","author":"Devlin","year":"2019","DOI":"10.18653\/v1\/N19-1423"},{"key":"2026072517363494100_btag495-B3","author":"Douze","year":"2024"},{"key":"2026072517363494100_btag495-B4","doi-asserted-by":"publisher","first-page":"457","DOI":"10.18653\/v1\/2024.bionlp-1.37","author":"El Khettari","year":"2024"},{"key":"2026072517363494100_btag495-B5","doi-asserted-by":"publisher","first-page":"103526","DOI":"10.1016\/j.jbi.2020.103526","article-title":"Clinical concept extraction: a methodology review","volume":"109","author":"Fu","year":"2020","journal-title":"J Biomed Inform"},{"key":"2026072517363494100_btag495-B6","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1186\/1471-2105-15-59","article-title":"Large-scale biomedical concept recognition: an evaluation of current automatic annotators and their parameters","volume":"15","author":"Funk","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2026072517363494100_btag495-B7","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s12911-024-02439-w","article-title":"An evaluation of GPT models for phenotype concept recognition","volume":"24","author":"Groza","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026072517363494100_btag495-B8","author":"Guu","year":"2020"},{"key":"2026072517363494100_btag495-B9","doi-asserted-by":"publisher","author":"Jin","year":"2018","DOI":"10.18653\/v1\/W18-5306"},{"key":"2026072517363494100_btag495-B10","doi-asserted-by":"publisher","first-page":"6769","DOI":"10.18653\/v1\/2020.emnlp-main.550","author":"Karpukhin","year":"2020"},{"key":"2026072517363494100_btag495-B11","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.52202\/068431-0151","article-title":"Cascadexml: rethinking transformers for end-to-end multi-resolution training in extreme multi-label classification","volume":"35","author":"Kharbanda","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026072517363494100_btag495-B12","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/K18-1050","article-title":"End-to-end neural entity linking","author":"Kolitsas","year":"2018."},{"key":"2026072517363494100_btag495-B13","doi-asserted-by":"publisher","author":"Lewis","year":"2019","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"2026072517363494100_btag495-B14","doi-asserted-by":"publisher","first-page":"4228","DOI":"10.18653\/v1\/2021.naacl-main.334","author":"Liu","year":"2021"},{"key":"2026072517363494100_btag495-B15","doi-asserted-by":"publisher","first-page":"596","DOI":"10.18653\/v1\/2025.acl-srw.39","author":"Liu","year":"2025"},{"key":"2026072517363494100_btag495-B16","doi-asserted-by":"publisher","first-page":"3718","DOI":"10.18653\/v1\/2026.eacl-long.172","author":"Liu","year":"2026"},{"key":"2026072517363494100_btag495-B17","doi-asserted-by":"publisher","first-page":"1051724","DOI":"10.3389\/frai.2022.1051724","article-title":"Clinical concept recognition: evaluation of existing systems on EHRS","volume":"5","author":"Lossio-Ventura","year":"2022","journal-title":"Front Artif Intell"},{"key":"2026072517363494100_btag495-B18","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1093\/bioinformatics\/btab019","article-title":"Phenotagger: a hybrid method for phenotype concept recognition using human phenotype ontology","volume":"37","author":"Luo","year":"2021","journal-title":"Bioinformatics"},{"key":"2026072517363494100_btag495-B19","author":"Mohan","year":"2019"},{"key":"2026072517363494100_btag495-B20","article-title":"Passage re-ranking with BERT.","author":"Nogueira"},{"key":"2026072517363494100_btag495-B21","doi-asserted-by":"publisher","first-page":"5835","DOI":"10.18653\/v1\/2021.naacl-main.466","author":"Qu","year":"2021"},{"key":"2026072517363494100_btag495-B22","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/978-3-030-43887-6_53","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"Rae","year":"2020"},{"key":"2026072517363494100_btag495-B23","doi-asserted-by":"publisher","first-page":"380","DOI":"10.18653\/v1\/2024.bionlp-1.29","author":"Shlyk","year":"2024"},{"key":"2026072517363494100_btag495-B24","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.18653\/v1\/2020.emnlp-main.130","author":"Wang","year":"2020"},{"key":"2026072517363494100_btag495-B25","doi-asserted-by":"publisher","first-page":"6397","DOI":"10.18653\/v1\/2020.emnlp-main.519","author":"Wu","year":"2020"},{"key":"2026072517363494100_btag495-B26","article-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval","author":"Xiong"},{"key":"2026072517363494100_btag495-B27","doi-asserted-by":"publisher","first-page":"3794","DOI":"10.1093\/bioinformatics\/btz142","article-title":"Meshprobenet: a self-attentive probe net for mesh indexing","volume":"35","author":"Xun","year":"2019","journal-title":"Bioinformatics"},{"key":"2026072517363494100_btag495-B28","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1186\/s12911-024-02516-0","article-title":"Homeostasis imbalance process ontology: a study on covid-19 infectious processes","volume":"23","author":"Yamagata","year":"2024","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026072517363494100_btag495-B29","first-page":"7267","article-title":"Fast multi-resolution transformer fine-tuning for extreme multi-label text classification","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag495\/68694042\/btag495.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/7\/btag495\/68694042\/btag495.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/7\/btag495\/68694042\/btag495.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T21:36:46Z","timestamp":1785015406000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag495\/8724507"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":29,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag495","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,7]]},"article-number":"btag495"}}