{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:28:17Z","timestamp":1761611297453},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,1,30]],"date-time":"2012-01-30T00:00:00Z","timestamp":1327881600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1186\/1471-2105-13-17","type":"journal-article","created":{"date-parts":[[2012,1,31]],"date-time":"2012-01-31T14:15:48Z","timestamp":1328019348000},"source":"Crossref","is-referenced-by-count":11,"title":["Training text chunkers on a silver standard corpus: can silver replace gold?"],"prefix":"10.1186","volume":"13","author":[{"given":"Ning","family":"Kang","sequence":"first","affiliation":[]},{"given":"Erik M","family":"van Mulligen","sequence":"additional","affiliation":[]},{"given":"Jan A","family":"Kors","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,1,30]]},"reference":[{"key":"5029_CR1","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MCAS.2006.1688199","volume":"6","author":"R Polikar","year":"2006","unstructured":"Polikar R: Ensemble based systems in decision making. IEEE Circuit Syst Mag 2006, 6: 21\u201345.","journal-title":"IEEE Circuit Syst Mag"},{"issue":"Suppl 2","key":"5029_CR2","doi-asserted-by":"publisher","first-page":"S2","DOI":"10.1186\/gb-2008-9-s2-s2","volume":"9","author":"L Smith","year":"2008","unstructured":"Smith L, Tanabe LK, Ando RJ, Kuo CJ, Chung IF, Hsu CN, Lin YS, Klinger R, Friedrich CM, Ganchev K, et al.: Overview of BioCreative II gene mention recognition. Genome Biol 2008, 9(Suppl 2):S2. 10.1186\/gb-2008-9-s2-s2","journal-title":"Genome Biol"},{"key":"5029_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3115\/1572340.1572342","volume-title":"Proceedings of the Workshop on BioNLP: Shared Task; Boulder","author":"J Kim","year":"2009","unstructured":"Kim J, Ohta T, Pyysalo S, Kano Y, Tsujii J: Overview of BioNLP'09 shared task on event extraction. Proceedings of the Workshop on BioNLP: Shared Task; Boulder 2009, 1\u20139."},{"key":"5029_CR4","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.jbi.2010.10.005","volume":"44","author":"N Kang","year":"2011","unstructured":"Kang N, van Mulligen EM, Kors JA: Comparing and combining chunkers of biomedical text. J Biomed Inform 2011, 44: 354\u2013360. 10.1016\/j.jbi.2010.10.005","journal-title":"J Biomed Inform"},{"key":"5029_CR5","first-page":"64","volume-title":"Proceedings of the Third International Symposium on Languages in Biology and Medicine; Jeju Island, South Korea","author":"D Rebholz-Schuhmann","year":"2009","unstructured":"Rebholz-Schuhmann D, Yepes AJ, van Mulligen EM, Kang N, Kors J, Milward D, Corbett P, Hahn U: The CALBC silver standard corpus - harmonizing multiple semantic annotations in a large biomedical corpus. Proceedings of the Third International Symposium on Languages in Biology and Medicine; Jeju Island, South Korea 2009, 64\u201372."},{"key":"5029_CR6","first-page":"101","volume-title":"Proceedings of the Fifth Linguistic Annotation Workshop; Portland","author":"MFM Chowdhury","year":"2011","unstructured":"Chowdhury MFM, Lavelli A: Assessing the practical usability of an automatically annotated corpus. Proceedings of the Fifth Linguistic Annotation Workshop; Portland 2011, 101\u2013109."},{"key":"5029_CR7","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1023\/A:1014348124664","volume":"36","author":"H Cunningham","year":"2002","unstructured":"Cunningham H: GATE, a general architecture for text engineering. Comput Humanities 2002, 36: 223\u2013254. 10.1023\/A:1014348124664","journal-title":"Comput Humanities"},{"key":"5029_CR8","first-page":"307","volume-title":"Proceedings of the Second BioCreative Challenge Evaluation Workshop; Valencia","author":"B Carpenter","year":"2007","unstructured":"Carpenter B: LingPipe for 99.99% recall of gene mentions. Proceedings of the Second BioCreative Challenge Evaluation Workshop; Valencia 2007, 307\u2013309."},{"key":"5029_CR9","first-page":"17","volume-title":"Proceedings of the AMIA Symposium; Washington DC","author":"AR Aronson","year":"2001","unstructured":"Aronson AR: Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program. Proceedings of the AMIA Symposium; Washington DC 2001, 17\u201321."},{"key":"5029_CR10","first-page":"65","volume-title":"Proceedings of the Joint BioLINK-Bio-Ontologies Meeting; Fortaleza","author":"E Buyko","year":"2006","unstructured":"Buyko E, Wermter J, Poprat M, Hahn U: Automatically adapting an NLP core engine to the biology domain. Proceedings of the Joint BioLINK-Bio-Ontologies Meeting; Fortaleza 2006, 65\u201368."},{"key":"5029_CR11","first-page":"1","volume-title":"Proceedings of the Second Meeting of the North American Chapter of the Association for Computational Linguistics on Language Technologies; Pittsburgh","author":"T Kudo","year":"2001","unstructured":"Kudo T, Matsumoto Y: Chunking with support vector machines. Proceedings of the Second Meeting of the North American Chapter of the Association for Computational Linguistics on Language Technologies; Pittsburgh 2001, 1\u20138."},{"key":"5029_CR12","first-page":"222","volume-title":"Proceedings of the Second International Joint Conference on Natural Language Processing; Jeju Island, South Korea","author":"Y Tateisi","year":"2005","unstructured":"Tateisi Y, Yakushiji A, Ohta T, Tsujii J: Syntax Annotation for the GENIA corpus. Proceedings of the Second International Joint Conference on Natural Language Processing; Jeju Island, South Korea 2005, 222\u2013227."},{"key":"5029_CR13","first-page":"61","volume-title":"Human Language Technology conference\/North American Chapter of the Association for Computational Linguistics Annual Meeting; Boston","author":"S Kulick","year":"2004","unstructured":"Kulick S, Bies A, Liberman M, Mandel M, McDonald R, Palmer M, Schein A, Ungar L, Winters S, White P: Integrated annotation for biomedical information extraction. Human Language Technology conference\/North American Chapter of the Association for Computational Linguistics Annual Meeting; Boston 2004, 61\u201368."},{"key":"5029_CR14","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1017\/S1351324904003523","volume":"10","author":"D Ferrucci","year":"2004","unstructured":"Ferrucci D, Lally A: UIMA: an architectural approach to unstructured information processing in the corporate research environment. Nat Lang Eng 2004, 10: 327\u2013348. 10.1017\/S1351324904003523","journal-title":"Nat Lang Eng"},{"key":"5029_CR15","first-page":"127","volume-title":"Proceedings of CoNLL-2000 and LLL-2000; Lisbon","author":"E Sang","year":"2000","unstructured":"Sang E, Buchholz S: Introduction to the CoNLL-2000 shared task: chunking. Proceedings of CoNLL-2000 and LLL-2000; Lisbon 2000, 127\u2013132."},{"key":"5029_CR16","unstructured":"PubMed stopword list[\n                    http:\/\/www.nlm.nih.gov\/bsd\/disted\/pubmedtutorial\/020_170.html\n                    \n                  ]"},{"key":"5029_CR17","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1006\/inco.1994.1009","volume":"108","author":"N Littlestone","year":"1994","unstructured":"Littlestone N, Warmuth MK: The weighted majority algorithm. Inform Comput 1994, 108: 212\u2013261. 10.1006\/inco.1994.1009","journal-title":"Inform Comput"},{"key":"5029_CR18","first-page":"443","volume-title":"Proceedings of the Seventh International Workshop on Frontiers in Handwriting Recognition; Amsterdam","author":"M Van Erp","year":"2000","unstructured":"Van Erp M, Schomaker L: Variants of the borda count method for combining ranked classifier hypotheses. Proceedings of the Seventh International Workshop on Frontiers in Handwriting Recognition; Amsterdam 2000, 443\u2013452."},{"key":"5029_CR19","first-page":"138","volume-title":"Proceedings of the 28th annual international ACM SIGIR conference on Research and Development in Information Retrieval; Salvador, Brazil","author":"K Seki","year":"2005","unstructured":"Seki K, Mostafa J: An application of text categorization methods to gene ontology annotation. Proceedings of the 28th annual international ACM SIGIR conference on Research and Development in Information Retrieval; Salvador, Brazil 2005, 138\u2013145."},{"key":"5029_CR20","doi-asserted-by":"publisher","first-page":"e18029","DOI":"10.1371\/journal.pone.0018029","volume":"6","author":"KW Boyack","year":"2011","unstructured":"Boyack KW, Newman D, Duhon RJ, Klavans R, Patek M, Biberstine JR, Schijvenaars B, Skupin A, Ma N, B\u00f6rner K: Clustering more than two million biomedical publications: comparing the accuracies of nine text-based similarity approaches. PLoS One 2011, 6: e18029. 10.1371\/journal.pone.0018029","journal-title":"PLoS One"},{"key":"5029_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3115\/1072133.1072204","volume-title":"Proceedings of the First International Conference on Human Language Technology Research; San Diego","author":"M Banko","year":"2001","unstructured":"Banko M, Brill E: Mitigating the paucity-of-data problem: exploring the effect of training corpus size on classifier performance for natural language processing. Proceedings of the First International Conference on Human Language Technology Research; San Diego 2001, 1\u20135."},{"key":"5029_CR22","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1017\/S135132490200298X","volume":"8","author":"D Yarowsky","year":"2002","unstructured":"Yarowsky D, Florian R: Evaluating sense disambiguation across diverse parameter spaces. Nat Lang Eng 2002, 8: 293\u2013310. 10.1017\/S135132490200298X","journal-title":"Nat Lang Eng"},{"key":"5029_CR23","first-page":"3433","volume-title":"Annual Conference of the International Speech Communication Association; Lisbon","author":"M Surdeanu","year":"2005","unstructured":"Surdeanu M, Turmo J, Comelles E: Named entity recognition from spontaneous open-domain speech. Annual Conference of the International Speech Communication Association; Lisbon 2005, 3433\u20133436."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-13-17.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-13-17\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-13-17.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,23]],"date-time":"2019-01-23T10:48:18Z","timestamp":1548240498000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-13-17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,1,30]]},"references-count":23,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,12]]}},"alternative-id":["5029"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-13-17","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,1,30]]},"article-number":"17"}}