{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T16:27:09Z","timestamp":1770481629836,"version":"3.49.0"},"reference-count":27,"publisher":"Elsevier BV","issue":"5","license":[{"start":{"date-parts":[[2009,10,1]],"date-time":"2009-10-01T00:00:00Z","timestamp":1254355200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2013,7,17]],"date-time":"2013-07-17T00:00:00Z","timestamp":1374019200000},"content-version":"vor","delay-in-days":1385,"URL":"https:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2009,10]]},"DOI":"10.1016\/j.jbi.2008.12.012","type":"journal-article","created":{"date-parts":[[2009,1,24]],"date-time":"2009-01-24T09:56:22Z","timestamp":1232790982000},"page":"905-911","source":"Crossref","is-referenced-by-count":91,"title":["Feature selection techniques for maximum entropy based biomedical named entity recognition"],"prefix":"10.1016","volume":"42","author":[{"given":"Sujan Kumar","family":"Saha","sequence":"first","affiliation":[]},{"given":"Sudeshna","family":"Sarkar","sequence":"additional","affiliation":[]},{"given":"Pabitra","family":"Mitra","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.jbi.2008.12.012_bib1","first-page":"39","article-title":"A maximum entropy approach to natural language processing","volume":"22","author":"Berger","year":"1996","journal-title":"Comput. Linguistic"},{"key":"10.1016\/j.jbi.2008.12.012_bib2","first-page":"153","article-title":"Survey and taxonomy of feature selection algorithms in intrusion detection system","volume":"4318","author":"Chen","year":"2006"},{"key":"10.1016\/j.jbi.2008.12.012_bib3","doi-asserted-by":"crossref","unstructured":"Collier N, Nobata C, Tsujii J. 2000. Extracting the names of genes and gene products with a hidden Markov model. In: Proceedings of COLING; 2000: p. 201\u20137.","DOI":"10.3115\/990820.990850"},{"key":"10.1016\/j.jbi.2008.12.012_bib4","doi-asserted-by":"crossref","unstructured":"Finkel J, Dingare S, Nguyen H, Nissim M, Manning C. 2004. Exploiting context for biomedical entity recognition: from syntax to the Web. In: Proceedings of the international joint workshop on natural language processing in biomedicine and its applications at COLING; 2004 (JNLPBA 2004).","DOI":"10.3115\/1567594.1567614"},{"key":"10.1016\/j.jbi.2008.12.012_bib5","doi-asserted-by":"crossref","unstructured":"Fodor IK. a survey of dimension reduction techniques. Technical report, Lawrence Livermore Nat Laboratory, Center for Applied Scientific Computing; 2002.","DOI":"10.2172\/15002155"},{"key":"10.1016\/j.jbi.2008.12.012_bib6","first-page":"1289","article-title":"An extensive empirical study of feature selection metrics for text classification","volume":"3","author":"Forman","year":"2003","journal-title":"J Machine Learning Res"},{"key":"10.1016\/j.jbi.2008.12.012_bib7","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."},{"key":"10.1016\/j.jbi.2008.12.012_bib8","unstructured":"Ganchev K, Crammer K, Pereira F, Mann G, Bellare K, McCallum A, et al. Penn\/UMass\/CHOP Biocreative II systems. In: Proceedings of the second biocreative challenge evaluation workshop; 2007."},{"key":"10.1016\/j.jbi.2008.12.012_bib9","doi-asserted-by":"crossref","unstructured":"Grishman R. The New York University System MUC-6 or Where\u2019s the Syntax? In: Proceedings of the sixth message understanding conference; 1995.","DOI":"10.3115\/1072399.1072415"},{"key":"10.1016\/j.jbi.2008.12.012_bib10","doi-asserted-by":"crossref","unstructured":"Kazama J, Makino T, Ohta Y, Tsujii J. Tuning support vector machines for biomedical named entity recognition. In: Proceedings of the workshop on natural language processing in the bio-medical domain at ACL; 2002: p. 1\u20138.","DOI":"10.3115\/1118149.1118150"},{"key":"10.1016\/j.jbi.2008.12.012_bib11","doi-asserted-by":"crossref","unstructured":"Kim J, Ohta T, Tateisi Y, Tsujii J. Genia Corpus\u2014a semantically annotated corpus for bio-textmining. Bioinformatics (Supplement: Eleventh International Conference on Intelligent Systems for Molecular Biology) 2003; 19: 180\u20132.","DOI":"10.1093\/bioinformatics\/btg1023"},{"key":"10.1016\/j.jbi.2008.12.012_bib12","doi-asserted-by":"crossref","unstructured":"Kim J, Ohta T, Tsuruoka Y, Tateisi Y, Collier N. Introduction to the bio-entity recognition task at JNLPBA. Nazarenko, editors, proceedings of the International Joint Workshop on Natural; 2004.","DOI":"10.3115\/1567594.1567610"},{"key":"10.1016\/j.jbi.2008.12.012_bib13","first-page":"652","article-title":"Banner: an executable survey of advances in biomedical named entity recognition","volume":"13","author":"Leaman","year":"2008","journal-title":"Pacific Symp Biocomput"},{"key":"10.1016\/j.jbi.2008.12.012_bib14","unstructured":"Lin YF, Tsai TH, Chou WC, Wu KP, Sung TY, Hsu WL. A maximum entropy approach to biomedical named entity recognition. In: Proceedings of 4th workshop on data mining in bioinformatics 2004; pages."},{"key":"10.1016\/j.jbi.2008.12.012_bib15","unstructured":"Miller S, Guinness J, Zamanian A. Name tagging with word clusters and discriminative training. In: Proceedings of the HLT-NAACL; 2004."},{"key":"10.1016\/j.jbi.2008.12.012_bib16","first-page":"382","article-title":"Biomedical named entity recognition: a poor knowledge HMM-based approach","volume":"4592","author":"Ponomareva","year":"2007","journal-title":"LNCS"},{"issue":"50","key":"10.1016\/j.jbi.2008.12.012_bib17","article-title":"BioInfer: a corpus for information extraction in the biomedical domain","volume":"8","author":"Pyysalo","year":"2007","journal-title":"BMC Bioinfo"},{"key":"10.1016\/j.jbi.2008.12.012_bib18","unstructured":"Saha SK, Mitra P, Sarkar S. Word clustering and word selection based feature reduction for MaxEnt based Hindi NER. In: Proceedings of ACL-08: HLT; 2008: p. 488\u201395."},{"key":"10.1016\/j.jbi.2008.12.012_bib19","doi-asserted-by":"crossref","unstructured":"Settles B. Biomedical named entity recognition using conditional random fields and rich feature sets. In: Proceedings of joint workshop on natural language processing in biomedicine and its applications (JNLPBA-2004); 2004.","DOI":"10.3115\/1567594.1567618"},{"key":"10.1016\/j.jbi.2008.12.012_bib20","doi-asserted-by":"crossref","unstructured":"Shen D, Zhang J, Zhou GD, Su J, Tan CL. Effective adaptation of a hidden markov model-based named entity recognizer for biomedical domain. In: Proceedings of ACL 2003 workshop on natural language processing in biomedicine; 2003: p. 49\u201356.","DOI":"10.3115\/1118958.1118965"},{"key":"10.1016\/j.jbi.2008.12.012_bib21","doi-asserted-by":"crossref","unstructured":"Song Y, Kim E, Lee GG, Yi BK. POSBIOTM-NER in the shared task of BioNLP\/NLPBA. In: Proceedings of the joint workshop on natural language processing in biomedicine and its applications (JNLPBA-2004); 2004.","DOI":"10.3115\/1567594.1567617"},{"issue":"1","key":"10.1016\/j.jbi.2008.12.012_bib22","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.eswa.2005.09.072","article-title":"Integrating linguistic knowledge into a conditional random field framework to identify biomedical named entities","volume":"30","author":"Tsai","year":"2006","journal-title":"Expert Syst Appl"},{"key":"10.1016\/j.jbi.2008.12.012_bib23","doi-asserted-by":"crossref","unstructured":"Ushioda A. Hierarchical clustering of words and application to NLP tasks. In: Proceedings of fourth workshop on very large corpora; 1996.","DOI":"10.3115\/993268.993390"},{"key":"10.1016\/j.jbi.2008.12.012_bib24","unstructured":"Uszkoreit J, Brants T. Distributed word clustering for large scale class-based language modeling in machine translation. In: Proceedings of ACL-08: HLT; 2008: p. 755\u201362."},{"issue":"Suppl. 1","key":"10.1016\/j.jbi.2008.12.012_bib25","doi-asserted-by":"crossref","first-page":"S2","DOI":"10.1186\/1471-2105-6-S1-S2","article-title":"BioCreAtIvE task 1A: gene mention finding evaluation","volume":"6","author":"Yeh","year":"2005","journal-title":"BMC Bioinfo"},{"key":"10.1016\/j.jbi.2008.12.012_bib26","unstructured":"You JM, Chen KJ. Improving context vector models by feature clustering for automatic thesaurus construction. In: Proceedings of the fifth SIGHAN workshop on chinese language processing; 2006: p. 1\u20138."},{"key":"10.1016\/j.jbi.2008.12.012_bib27","doi-asserted-by":"crossref","unstructured":"Zhou GD, Su J. Exploring deep knowledge resources in biomedical name recognition. In: Proceedings of joint workshop on natural language processing in biomedicine and its applications (JNLPBA-2004); 2004: p. 96\u20139.","DOI":"10.3115\/1567594.1567616"}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046409000033?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046409000033?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T06:09:19Z","timestamp":1738908559000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046409000033"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,10]]},"references-count":27,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2009,10]]}},"alternative-id":["S1532046409000033"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2008.12.012","relation":{},"ISSN":["1532-0464"],"issn-type":[{"value":"1532-0464","type":"print"}],"subject":[],"published":{"date-parts":[[2009,10]]}}}