{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:00:31Z","timestamp":1791352831187,"version":"4.3.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,2,21]],"date-time":"2015-02-21T00:00:00Z","timestamp":1424476800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/s12859-015-0487-2","type":"journal-article","created":{"date-parts":[[2015,2,20]],"date-time":"2015-02-20T05:34:49Z","timestamp":1424410489000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Identifying named entities from PubMed\u00ae for enriching semantic categories"],"prefix":"10.1186","volume":"16","author":[{"given":"Sun","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"W John","family":"Wilbur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,2,21]]},"reference":[{"issue":"1","key":"487_CR1","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1093\/bib\/6.1.57","volume":"6","author":"AM Cohen","year":"2005","unstructured":"Cohen AM, Hersh WR. A survey of current work in biomedical text mining. Briefings in Bioinf. 2005; 6(1):57\u201371.","journal-title":"Briefings in Bioinf."},{"issue":"7","key":"487_CR2","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1186\/gb-2005-6-7-224","volume":"6","author":"M Krallinger","year":"2005","unstructured":"Krallinger M, Valencia A. Text-mining and information-retrieval services for molecular biology. Genome Biol. 2005; 6(7):224.","journal-title":"Genome Biol."},{"issue":"5","key":"487_CR3","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1093\/bib\/bbt006","volume":"15","author":"C Li","year":"2014","unstructured":"Li C, Liakata M, Rebholz-Schuhmann D. Biological network extraction from scientific literature: state of the art and challenges. Briefings in Bioinf. 2014; 15(5):856\u201377.","journal-title":"Briefings in Bioinf."},{"issue":"6","key":"487_CR4","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1016\/j.jbi.2004.08.004","volume":"37","author":"M Krauthammer","year":"2004","unstructured":"Krauthammer M, Nenadic G. Term identification in the biomedical literature. J Biomed Inform. 2004; 37(6):512\u201326.","journal-title":"J Biomed Inform."},{"key":"487_CR5","volume-title":"Proceedings of the 9th Pacific Rim International Conference on Artificial Intelligence","author":"X Zhou","year":"2006","unstructured":"Zhou X, Zhang X, Hu X. MaxMatcher: Biological concept extraction using approximate dictionary lookup. In: Proceedings of the 9th Pacific Rim International Conference on Artificial Intelligence. Berlin, Heidelberg: Springer: 2006. p. 1145\u20139."},{"issue":"1","key":"487_CR6","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.jbi.2011.10.007","volume":"45","author":"S Jonnalagadda","year":"2012","unstructured":"Jonnalagadda S, Cohen T, Wu S, Gonzalez G. Enhancing clinical concept extraction with distributional semantics. J Biomed Informatics. 2012; 45(1):129\u201340.","journal-title":"J Biomed Informatics"},{"issue":"1","key":"487_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/ijkdb.2014010101","volume":"4","author":"JAL Ventura","year":"2014","unstructured":"Ventura JAL, Jonquet C, Roche M, Teisseire M. Towards a mixed approach to extract biomedical terms from text corpus. Int J Knowledge Discovery Bioinf. 2014; 4(1):1\u201315.","journal-title":"Int J Knowledge Discovery Bioinf."},{"issue":"4","key":"487_CR8","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/S1532-0464(03)00014-5","volume":"35","author":"L Hirschman","year":"2002","unstructured":"Hirschman L, Morgan AA, Yeh AS. Rutabaga by any other name: extracting biological names. J Biomed Inform. 2002; 35(4):247\u201359.","journal-title":"J Biomed Inform."},{"key":"487_CR9","doi-asserted-by":"crossref","unstructured":"Tuason O, Chen L, Liu H, Blake JA, Friedman C. Biological nomenclatures: a source of lexical knowledge and ambiguity. In: Proceedings of the Pacific Symposium on Biocomputing: 2004. p. 238\u201349.","DOI":"10.1142\/9789812704856_0023"},{"key":"487_CR10","unstructured":"Aronson AR. Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program. In: Proceedings of the Pacific Symposium on Biocomputing: 2001. p. 17\u201321."},{"key":"487_CR11","volume-title":"Proceedings of the 15th Conference on Computational Linguistics - Volume 2","author":"S Ananiadou","year":"1994","unstructured":"Ananiadou S. A methodology for automatic term recognition. In: Proceedings of the 15th Conference on Computational Linguistics - Volume 2. Stroudsburg, PA, USA: Association for Computational Linguistics: 1994. p. 1034\u20138."},{"key":"487_CR12","unstructured":"Fukuda K, Tsunoda T, Tamura A, Takagi T. Toward information extraction: Identifying protein names from biological papers. In: Proceedings of the Pacific Symposium on Biocomputing: 1998. p. 707\u201318."},{"issue":"1","key":"487_CR13","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1093\/bioinformatics\/19.1.135","volume":"19","author":"R Gaizauskas","year":"2003","unstructured":"Gaizauskas R, Demetriou G, Artymiuk PJ, Willett P. Protein structures and information extraction from biological texts: the PASTA system. Bioinformatics. 2003; 19(1):135\u201343.","journal-title":"Bioinformatics"},{"issue":"7","key":"487_CR14","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1093\/bioinformatics\/14.7.600","volume":"14","author":"MA Andrade","year":"1998","unstructured":"Andrade MA, Valencia A. Automatic extraction of keywords from scientific text: application to the knowledge domain of protein families. Bioinformatics. 1998; 14(7):600\u20137.","journal-title":"Bioinformatics"},{"issue":"Suppl 1","key":"487_CR15","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1471-2105-6-S1-S8","volume":"6","author":"T Mitsumori","year":"2005","unstructured":"Mitsumori T, Fation S, Murata M, Doi K, Doi H. Gene\/protein name recognition based on support vector machine using dictionary as features. BMC Bioinformatics. 2005; 6(Suppl 1):8.","journal-title":"BMC Bioinformatics"},{"issue":"Suppl 1","key":"487_CR16","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/1471-2105-6-S1-S6","volume":"6","author":"R McDonald","year":"2005","unstructured":"McDonald R, Pereira F. Identifying gene and protein mentions in text using conditional random fields. BMC Bioinformatics. 2005; 6(Suppl 1):6.","journal-title":"BMC Bioinformatics"},{"issue":"Suppl 1","key":"487_CR17","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/1471-2105-6-S1-S3","volume":"6","author":"L Tanabe","year":"2005","unstructured":"Tanabe L, Xie N, Thom LH, Matten W, Wilbur WJ. GENETAG: a tagged corpus for gene\/protein named entity recognition. BMC Bioinformatics. 2005; 6(Suppl 1):3.","journal-title":"BMC Bioinformatics"},{"issue":"Suppl 1","key":"487_CR18","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1093\/bioinformatics\/btg1023","volume":"19","author":"J-D Kim","year":"2003","unstructured":"Kim J-D, Ohta T, Tateisi Y, Tsujii J. GENIA corpus\u2013a semantically annotated corpus for bio-text mining. Bioinformatics. 2003; 19(Suppl 1):180\u20132.","journal-title":"Bioinformatics"},{"key":"487_CR19","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/1758-2946-6-17","volume":"6","author":"S Eltyeb","year":"2014","unstructured":"Eltyeb S, Salim N. Chemical named entities recognition: a review on approaches and applications. J Cheminformatics. 2014; 6:17.","journal-title":"J Cheminformatics"},{"key":"487_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jbi.2013.12.006","volume":"47","author":"RI Do\u011fan","year":"2014","unstructured":"Do\u011fan RI, Leaman R, Lu Z. NCBI disease corpus: a resource for disease name recognition and concept normalization. J Biomed Informatics. 2014; 47:1\u201310.","journal-title":"J Biomed Informatics"},{"key":"487_CR21","first-page":"5","volume":"1","author":"KM Hettne","year":"2010","unstructured":"Hettne KM, van Mulligen EM, Schuemie MJ, Schijvenaars BJA, Kors JA. Rewriting and suppressing UMLS terms for improved biomedical term identification. J Biomed Informatics. 2010; 1:5.","journal-title":"J Biomed Informatics"},{"key":"487_CR22","unstructured":"The Unified Medical Language System. http:\/\/www.nlm.nih.gov\/research\/umls."},{"key":"487_CR23","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1136\/jamia.2009.002733","volume":"17","author":"AR Aronson","year":"2010","unstructured":"Aronson AR, Lang F-M. An overview of MetaMap: historical perspective and recent advances. J Am Med Informatics Assoc. 2010; 17:229\u201336.","journal-title":"J Am Med Informatics Assoc."},{"issue":"6","key":"487_CR24","doi-asserted-by":"publisher","first-page":"1088","DOI":"10.1016\/j.jbi.2013.08.004","volume":"46","author":"S Zhang","year":"2013","unstructured":"Zhang S, Elhadad N. Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts. J Biomed Informatics. 2013; 46(6):1088\u201398.","journal-title":"J Biomed Informatics"},{"key":"487_CR25","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.jbi.2013.11.008","volume":"48","author":"GT Gobbel","year":"2014","unstructured":"Gobbel GT, Reeves R, Jayaramaraja S, Giuse D, Speroff T, Brown SH, et al. Development and evaluation of RapTAT: a machine learning system for concept mapping of phrases from medical narratives. J Biomed Inform. 2014; 48:54\u201365.","journal-title":"J Biomed Inform."},{"key":"487_CR26","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1136\/amiajnl-2011-000744","volume":"19","author":"ST Wu","year":"2012","unstructured":"Wu ST, Liu H, Li D, Tao C, Musen MA, Chute CG, et al. Unified Medical Language System term occurrences in clinical notes: a large-scale corpus analysis. J Am Med Informatics Assoc. 2012; 19:149\u201356.","journal-title":"J Am Med Informatics Assoc."},{"key":"487_CR27","unstructured":"McCray AT, Bodenreider O, Malley JD, Browne AC. Evaluating UMLS strings for natural language processing. In: Proceedings of the AMIA Annual Symposium. American Medical Informatics Association: 2001. p. 448\u201352."},{"key":"487_CR28","unstructured":"Srinivasan S, Rindflesch TC, Hole WT, Aronson AR, Mork JG. Finding UMLS Metathesaurus concepts in MEDLINE. In: Proceedings of the AMIA Annual Symposium. American Medical Informatics Association: 2002. p. 727\u201331."},{"key":"487_CR29","unstructured":"Xu R, Musen MA, Shah NH. A comprehensive analysis of five million UMLS Metathesaurus terms using eighteen million MEDLINE citations. In: AMIA Annual Symposium Proceedings. American Medical Informatics Association: 2010. p. 907\u201311."},{"key":"487_CR30","unstructured":"Tanabe L, Thom LH, Matten W, Comeau DC, Wilbur WJ. SemCat: Semantically categorized entities for genomics. In: AMIA Annual Symposium Proceedings. American Medical Informatics Association: 2006. p. 754\u20138."},{"key":"487_CR31","doi-asserted-by":"publisher","first-page":"042","DOI":"10.1093\/database\/bas042","volume":"2012","author":"S Kim","year":"2012","unstructured":"Kim S, Kim W, Wei C-H, Lu Z, Wilbur WJ. Prioritizing PubMed articles for the Comparative Toxicogenomic Database utilizing semantic information. Database. 2012; 2012:042.","journal-title":"Database"},{"issue":"Suppl 1","key":"487_CR32","first-page":"52","volume":"39","author":"D Maglott","year":"2014","unstructured":"Maglott D, Ostell J, Pruitt KD, Tatusova T. Entrez Gene: gene-centered information at NCBI. Nucleic Acids Res. 2014; 39(Suppl 1):52\u20137.","journal-title":"Nucleic Acids Res."},{"issue":"D1","key":"487_CR33","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1093\/nar\/gkt1140","volume":"42","author":"TU Consortium","year":"2014","unstructured":"Consortium TU. Activities at the Universal Protein Resource (UniProt). Nucleic Acids Res. 2014; 42(D1):191\u20138.","journal-title":"Nucleic Acids Res."},{"issue":"1-2","key":"487_CR34","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1002\/cfg.451","volume":"6","author":"K Verspoor","year":"2005","unstructured":"Verspoor K. Towards a semantic lexicon for biological language processing. Comp Funct Genomics. 2005; 6(1-2):61\u20136.","journal-title":"Comp Funct Genomics"},{"key":"487_CR35","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1197\/jamia.M2314","volume":"14","author":"J-W Fan","year":"2007","unstructured":"Fan J-W, Friedman C. Semantic classification of biomedical concepts using distributional similarity. J Am Med Informatics Assoc. 2007; 14:467\u201377.","journal-title":"J Am Med Informatics Assoc."},{"issue":"17","key":"487_CR36","doi-asserted-by":"publisher","first-page":"1971","DOI":"10.1093\/bioinformatics\/btn343","volume":"24","author":"J-W Fan","year":"2008","unstructured":"Fan J-W, Friedman C. Semantic reclassification of the UMLS concepts. Bioinformatics. 2008; 24(17):1971\u20133.","journal-title":"Bioinformatics"},{"key":"487_CR37","volume-title":"Proceedings of the ACL-02 Workshop on Natural Language Processing in the Biomedical Domain","author":"O Bodenreider","year":"2002","unstructured":"Bodenreider O, Rindflesch TC, Burgun A. Unsupervised, corpus-based method for extending a biomedical terminology. In: Proceedings of the ACL-02 Workshop on Natural Language Processing in the Biomedical Domain. Stroudsburg, PA, USA: Association for Computational Linguistics: 2002. p. 53\u201360."},{"key":"487_CR38","doi-asserted-by":"crossref","unstructured":"Tanabe L, Wilbur WJ. A priority model for named entities. In: Proceedings of the HLT-NAACL BioNLP Workshop on Linking Natural Language and Biology: 2006. p. 33\u201340.","DOI":"10.3115\/1654415.1654422"},{"issue":"Suppl 3","key":"487_CR39","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/2041-1480-3-S3-S3","volume":"3","author":"L Yeganova","year":"2012","unstructured":"Yeganova L, Kim W, Comeau DC, Wilbur WJ. Finding biomedical categories in Medline. J Biomed Semantics. 2012; 3(Suppl 3):3.","journal-title":"J Biomed Semantics"},{"issue":"1","key":"487_CR40","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.artint.2005.03.001","volume":"165","author":"O Etzioni","year":"2005","unstructured":"Etzioni O, Cafarella M, Downey D, Popescu A-M, Shaked T, et al. Unsupervised named-entity extraction from the Web: An experimental study. Artif Intell. 2005; 165(1):91\u2013134.","journal-title":"Artif Intell."},{"key":"487_CR41","volume-title":"Proceedings of the 14th Conference on Computational Linguistics","author":"MA Hearst","year":"1992","unstructured":"Hearst MA. Automatic acquisition of hyponyms from large text corpora. In: Proceedings of the 14th Conference on Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics: 1992. p. 539\u201345."},{"key":"487_CR42","unstructured":"Wilbur WJ, Kim W. Flexible phrase based query handling algorithms. In: Proceedings of the ASIST 2001 Annual Meeting: 2001. p. 438\u201349."},{"key":"487_CR43","doi-asserted-by":"crossref","unstructured":"Zhang T. Solving large scale linear prediction problems using stochastic gradient descent algorithms. In: Proceedings of the 21st International Conference on Machine Learning: 2004. p. 919\u201326.","DOI":"10.1145\/1015330.1015332"},{"issue":"6","key":"487_CR44","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/s10791-010-9126-8","volume":"13","author":"LH Smith","year":"2010","unstructured":"Smith LH, Wilbur WJ. Finding related sentence pairs in MEDLINE. Inf Retrieval. 2010; 13(6):601\u201317.","journal-title":"Inf Retrieval"},{"issue":"Suppl 8","key":"487_CR45","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/1471-2105-12-S8-S9","volume":"12","author":"S Kim","year":"2011","unstructured":"Kim S, Wilbur WJ. Classifying protein-protein interaction articles using word and syntactic features. BMC Bioinformatics. 2011; 12(Suppl 8):9.","journal-title":"BMC Bioinformatics"},{"key":"487_CR46","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/2041-1480-3-3","volume":"3","author":"H Liu","year":"2012","unstructured":"Liu H, Christiansen T, Baumgartner WA, Verspoor K. BioLemmatizer: a lemmatization tool for morphological processing of biomedical text. J Biomed Semantics. 2012; 3:3.","journal-title":"J Biomed Semantics"},{"issue":"14","key":"487_CR47","doi-asserted-by":"publisher","first-page":"2320","DOI":"10.1093\/bioinformatics\/bth227","volume":"20","author":"L Smith","year":"2004","unstructured":"Smith L, Rindflesch T, Wilbur WJ. MedPost: a part-of-speech tagger for biomedical text. Bioinformatics. 2004; 20(14):2320\u20131.","journal-title":"Bioinformatics"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-015-0487-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-015-0487-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-015-0487-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-015-0487-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T19:58:33Z","timestamp":1747684713000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-015-0487-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2,21]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["487"],"URL":"https:\/\/doi.org\/10.1186\/s12859-015-0487-2","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,2,21]]},"assertion":[{"value":"23 October 2014","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2015","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2015","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"57"}}