{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T08:28:45Z","timestamp":1674635325359},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2009,12,1]],"date-time":"2009-12-01T00:00:00Z","timestamp":1259625600000},"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":[[2009,12]]},"DOI":"10.1186\/1471-2105-10-403","type":"journal-article","created":{"date-parts":[[2009,12,9]],"date-time":"2009-12-09T13:19:24Z","timestamp":1260364764000},"source":"Crossref","is-referenced-by-count":7,"title":["Investigating heterogeneous protein annotations toward cross-corpora utilization"],"prefix":"10.1186","volume":"10","author":[{"given":"Yue","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jin-Dong","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Rune","family":"S\u00e6tre","sequence":"additional","affiliation":[]},{"given":"Sampo","family":"Pyysalo","sequence":"additional","affiliation":[]},{"given":"Jun'ichi","family":"Tsujii","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2009,12,9]]},"reference":[{"issue":"Suppl 1","key":"3133_CR1","doi-asserted-by":"publisher","first-page":"i180","DOI":"10.1093\/bioinformatics\/btg1023","volume":"19","author":"JD Kim","year":"2003","unstructured":"Kim JD, Ohta T, Tateisi Y, Tsujii J: GENIA corpus - a semantically annotated corpus for bio-textmining. Bioinformatics 2003, 19(Suppl 1):i180-i182. 10.1093\/bioinformatics\/btg1023","journal-title":"Bioinformatics"},{"issue":"Suppl 1","key":"3133_CR2","doi-asserted-by":"publisher","first-page":"S3","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):S3-S9. 10.1186\/1471-2105-6-S1-S3","journal-title":"BMC Bioinformatics"},{"key":"3133_CR3","first-page":"171","volume-title":"Advances in Neural Information Processing Systems","author":"R Bunescu","year":"2006","unstructured":"Bunescu R, Mooney R: Subsequence kernels for relation extraction. In Advances in Neural Information Processing Systems. Volume 18. 2nd edition. Edited by: Weiss Y, Sch\u00f6lkopf B, Platt J. Cambridge, MA: MIT Press; 2006:171\u2013178.","edition":"2"},{"key":"3133_CR4","volume-title":"Proceedings of the Workshop on Text Mining, Ontologies and Natural Language Processing in Biomedicine: 20-21 March 2006; Manchester, UK","author":"MA Mandel","year":"2006","unstructured":"Mandel MA: Integrated annotation of biomedical text: creating the PennBioIE corpus. Proceedings of the Workshop on Text Mining, Ontologies and Natural Language Processing in Biomedicine: 20\u201321 March 2006; Manchester, UK 2006."},{"key":"3133_CR5","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1089\/106652703322756104","volume":"10","author":"H Shatkay","year":"2003","unstructured":"Shatkay H, Feldman R: Mining the biomedical literature in the genomic era: an overview. Journal of Computational Biology 2003, 10: 821\u2013855. 10.1089\/106652703322756104","journal-title":"Journal of Computational Biology"},{"key":"3133_CR6","first-page":"70","volume-title":"Proceedings of the Joint workshop on Natural Language Processing in Biomedicine and its Applications: 28-29 August 2004; Geneva, Switzerland","author":"JD Kim","year":"2004","unstructured":"Kim JD, Ohta T, Tsuruoka Y, Tateisi Y, Collier N: Introduction to the bio-entity recognition task at JNLPBA. Proceedings of the Joint workshop on Natural Language Processing in Biomedicine and its Applications: 28\u201329 August 2004; Geneva, Switzerland 2004, 70\u201375."},{"key":"3133_CR7","first-page":"7","volume-title":"Proceedings of the Second BioCreative Challenge Evaluation Workshop: 23-25 April 2007; Madrid, Spain","author":"J Wilbur","year":"2007","unstructured":"Wilbur J, Smith L, Tanabe L: BioCreative 2. Gene mention task. Proceedings of the Second BioCreative Challenge Evaluation Workshop: 23\u201325 April 2007; Madrid, Spain 2007, 7\u201316."},{"key":"3133_CR8","doi-asserted-by":"publisher","first-page":"2794","DOI":"10.1093\/bioinformatics\/bti414","volume":"21","author":"Y Song","year":"2005","unstructured":"Song Y, Kim E, Lee GG, Yi BK: POSBIOTM-NER: a trainable biomedical named-entity recognition system. Bioinformatics 2005, 21: 2794\u20132796. 10.1093\/bioinformatics\/bti414","journal-title":"Bioinformatics"},{"key":"3133_CR9","first-page":"105","volume-title":"Proceedings of the Second BioCreative Challenge Evaluation Workshop: 23-25 April 2007; Madrid, Spain","author":"CJ Kuo","year":"2007","unstructured":"Kuo CJ, Chang YM, Huang HS, Lin KT, Yang BH, Lin YS, Hsu CN, Chung IF: Rich feature set, unification of bidirectional parsing and dictionary filtering for high F-score gene mention tagging. Proceedings of the Second BioCreative Challenge Evaluation Workshop: 23\u201325 April 2007; Madrid, Spain 2007, 105\u2013107."},{"key":"3133_CR10","first-page":"141","volume-title":"Proceedings of the Third International Symposium on Semantic Mining in Biomedicine: 1-3 September 2008; Turku, Finland","author":"R Kabiljo","year":"2008","unstructured":"Kabiljo R, Shepherd A: Protein name tagging in the immunological domain. Proceedings of the Third International Symposium on Semantic Mining in Biomedicine: 1\u20133 September 2008; Turku, Finland 2008, 141\u2013144."},{"key":"3133_CR11","first-page":"40","volume-title":"Proceedings of the Data and Text Mining in Integrative Biology Workshop: 18-22 September 2006; Berlin, Germany","author":"C N\u00e9dellec","year":"2006","unstructured":"N\u00e9dellec C, Bessi\u00e8res P, Bossy R, Kotoujansky A, Manine AP: Annotation guidelines for machine learning-based named entity recognition in microbiology. Proceedings of the Data and Text Mining in Integrative Biology Workshop: 18\u201322 September 2006; Berlin, Germany 2006, 40\u201354."},{"key":"3133_CR12","unstructured":"The GENIA tagger[\n                    http:\/\/www-tsujii.is.s.u-tokyo.ac.jp\/GENIA\/tagger\/\n                    \n                  ]"},{"key":"3133_CR13","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/S1386-5056(02)00052-7","volume":"67","author":"K Franz\u00e9n","year":"2002","unstructured":"Franz\u00e9n K, Eriksson G, Olsson F, Asker L, Lid\u00e9n P, C\u00f6ster J: Protein names and how to find them. International Journal of Medical Informatics 2002, 67: 49\u201361. 10.1016\/S1386-5056(02)00052-7","journal-title":"International Journal of Medical Informatics"},{"key":"3133_CR14","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1186\/1471-2105-7-92","volume":"7","author":"RTH Tsai","year":"2006","unstructured":"Tsai RTH, Wu SH, Chou WC, Lin YC, He D, Hsiang J, Sung TY, Hsu WL: Various criteria in the evaluation of biomedical named entity recognition. BMC Bioinformatics 2006, 7: 92\u201399. 10.1186\/1471-2105-7-92","journal-title":"BMC Bioinformatics"},{"key":"3133_CR15","doi-asserted-by":"publisher","first-page":"82","DOI":"10.3115\/1289189.1289260","volume-title":"Proceedings of the Human Language Technology Conference: 24-27 March 2002, San Diego, USA","author":"T Ohta","year":"2002","unstructured":"Ohta T, Tateisi Y, Kim JD, Mima H, Tsujii J: The GENIA corpus: an annotated research abstract corpus in molecular biology domain. Proceedings of the Human Language Technology Conference: 24\u201327 March 2002, San Diego, USA 2002, 82\u201386."},{"key":"3133_CR16","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.artmed.2004.07.016","volume":"33","author":"R Bunescu","year":"2005","unstructured":"Bunescu R, Ge R, Kate RJ, Marcotte EM, Mooney RJ, Ramani AK, Wong YW: Comparative experiments on learning information extractors for proteins and their interactions. Artificial Intelligence in Medicine 2005, 33: 139\u2013155. 10.1016\/j.artmed.2004.07.016","journal-title":"Artificial Intelligence in Medicine"},{"key":"3133_CR17","unstructured":"GenBank: NIH Genetic Sequence Database[\n                    http:\/\/www.ncbi.nlm.nih.gov\/Genbank\/\n                    \n                  ]"},{"issue":"Suppl 1","key":"3133_CR18","doi-asserted-by":"publisher","first-page":"S97","DOI":"10.1093\/bioinformatics\/17.suppl_1.S97","volume":"17","author":"V Hatzivassiloglou","year":"2001","unstructured":"Hatzivassiloglou V, Duboue PA, Rzhetsky A: Disambiguating proteins, genes, and RNA in text: a machine learning approach. Bioinformatics 2001, 17(Suppl 1):S97-S106.","journal-title":"Bioinformatics"},{"key":"3133_CR19","doi-asserted-by":"publisher","first-page":"947","DOI":"10.3115\/992730.992783","volume-title":"Proceedings of the 18th International Conference on Computational Linguistics: July 31 - August 4 Saarbr\u00fccken, Germany","author":"A Yeh","year":"2000","unstructured":"Yeh A: More accurate tests for the statistical significance of result differences. Proceedings of the 18th International Conference on Computational Linguistics: July 31 - August 4 Saarbr\u00fccken, Germany 2000, 947\u2013953."},{"key":"3133_CR20","volume-title":"Computer-Intensive Methods for Testing Hypotheses: An Introduction","author":"EW Noreen","year":"1989","unstructured":"Noreen EW: Computer-Intensive Methods for Testing Hypotheses: An Introduction. Wiley-Interscience; 1989."},{"key":"3133_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-4541-9","volume-title":"An Introduction to the Bootstrap","author":"B Efron","year":"1993","unstructured":"Efron B, Tibshirani RJ: An Introduction to the Bootstrap. New York: Chapman & Hall; 1993."},{"key":"3133_CR22","first-page":"559","volume":"2","author":"EFTK Sang","year":"2002","unstructured":"Sang EFTK: Memory-Based shallow parsing. Journal of Machine Learning Research 2002, 2: 559\u2013594.","journal-title":"Journal of Machine Learning Research"},{"key":"3133_CR23","first-page":"23","volume-title":"Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing: 1989; Glasgow, Scotland","author":"L Gillick","year":"1989","unstructured":"Gillick L, Cox S: Some statistical issues in the comparison of speech recognition algorithms. Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing: 1989; Glasgow, Scotland 1989, 23\u201326."},{"key":"3133_CR24","first-page":"213","volume-title":"Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: 28-30 May 2003; Edmonton, Canada","author":"F Sha","year":"2003","unstructured":"Sha F, Pereira F: Shallow parsing with conditional random fields. Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: 28\u201330 May 2003; Edmonton, Canada 2003, 213\u2013220."},{"key":"3133_CR25","first-page":"841","volume-title":"Proceedings of the 22nd International Conference on Computational Linguistics: 18-22 August 2008; Manchester, UK","author":"X Sun","year":"2008","unstructured":"Sun X, Morency LP, Okanohara D, Tsujii J: Modeling latent-dynamic in shallow parsing: a latent conditional model with improved inference. Proceedings of the 22nd International Conference on Computational Linguistics: 18\u201322 August 2008; Manchester, UK 2008, 841\u2013848."},{"key":"3133_CR26","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/1747-5333-2-4","volume":"2","author":"HL Johnson","year":"2007","unstructured":"Johnson HL, Baumgartner WA, Krallinger M, Cohen KB, Hunter L: Corpus refactoring: a feasibility study. Journal of Biomedical Discovery and Collaboration 2007, 2: 4\u201314. 10.1186\/1747-5333-2-4","journal-title":"Journal of Biomedical Discovery and Collaboration"},{"issue":"Suppl 3","key":"3133_CR27","doi-asserted-by":"publisher","first-page":"S6","DOI":"10.1186\/1471-2105-9-S3-S6","volume":"9","author":"S Pyysalo","year":"2008","unstructured":"Pyysalo S, Airola A, Heimonen J, Bj\u00f6rne J, Ginter F, Salakoski T: Comparative analysis of five protein-protein interaction corpora. BMC Bioinformatics 2008, 9(Suppl 3):S6-S16. 10.1186\/1471-2105-9-S3-S6","journal-title":"BMC Bioinformatics"},{"key":"3133_CR28","first-page":"256","volume-title":"Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics: 23-30 June 2007; Prague, Czech Republic","author":"H Daum\u00e9 III","year":"2007","unstructured":"Daum\u00e9 H III: Frustratingly easy domain adaptation. Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics: 23\u201330 June 2007; Prague, Czech Republic 2007, 256\u2013263."},{"key":"3133_CR29","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/ICDMW.2007.109","volume-title":"Proceedings of the Seventh IEEE International Conference on Data Mining Workshops: 28-31 October 2007; Omaha, Nebraska, USA","author":"A Arnold","year":"2007","unstructured":"Arnold A, Nallapati R, Cohen WW: A comparative study of methods for transductive transfer learning. Proceedings of the Seventh IEEE International Conference on Data Mining Workshops: 28\u201331 October 2007; Omaha, Nebraska, USA 2007, 77\u201382."},{"key":"3133_CR30","first-page":"595","volume-title":"Proceedings of The Fifth International Conference on Language Resources and Evaluation: 24-26 MAY 2006; Genoa, Italy","author":"B Alex","year":"2006","unstructured":"Alex B, Nissim M, Grover C: The impact of annotation on the performance of protein tagging in biomedical text. Proceedings of The Fifth International Conference on Language Resources and Evaluation: 24\u201326 MAY 2006; Genoa, Italy 2006, 595\u2013600."},{"key":"3133_CR31","first-page":"117","volume-title":"Proceedings of the Third International Symposium on Semantic Mining in Biomedicine: 1-3 September 2008; Turku, Finland","author":"Y Wang","year":"2008","unstructured":"Wang Y, Kim JD, S\u00e6tre R, Tsujii J: Exploring the compatibility of heterogeneous protein annotations toward corpus integration. Proceedings of the Third International Symposium on Semantic Mining in Biomedicine: 1\u20133 September 2008; Turku, Finland 2008, 117\u2013124."},{"key":"3133_CR32","unstructured":"The GENIA corpus[\n                    http:\/\/www-tsujii.is.s.u-tokyo.ac.jp\/~genia\/topics\/Corpus\/\n                    \n                  ]"},{"key":"3133_CR33","unstructured":"The JNLPBA corpus[\n                    http:\/\/research.nii.ac.jp\/~collier\/workshops\/JNLPBA04st.htm\n                    \n                  ]"},{"key":"3133_CR34","first-page":"38","volume-title":"Proceedings of the ACL-ISMB Workshop on Linking Biological Literature, Ontologies and Databases: Mining Biological Semantics: 24 June 2005; Detroit, USA","author":"KB Cohen","year":"2005","unstructured":"Cohen KB, Fox L, Ogren PV, Hunter L: Corpus design for biomedical natural language processing. Proceedings of the ACL-ISMB Workshop on Linking Biological Literature, Ontologies and Databases: Mining Biological Semantics: 24 June 2005; Detroit, USA 2005, 38\u201345."},{"key":"3133_CR35","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 Bioinformatics 2005, 6: 57\u201371. 10.1093\/bib\/6.1.57","journal-title":"Briefings in Bioinformatics"},{"issue":"Suppl 1","key":"3133_CR36","doi-asserted-by":"publisher","first-page":"S7","DOI":"10.1186\/1471-2105-6-S1-S7","volume":"6","author":"G Zhou","year":"2005","unstructured":"Zhou G, Shen D, Zhang J, Su J, Tan S: Recognition of protein and gene names from text using an ensemble of classifiers and effective abbreviation resolution. BMC Bioinformatics 2005, 6(Suppl 1):S7-S13. 10.1186\/1471-2105-6-S1-S7","journal-title":"BMC Bioinformatics"},{"issue":"Suppl 3","key":"3133_CR37","doi-asserted-by":"publisher","first-page":"S3","DOI":"10.1186\/1471-2105-7-S3-S3","volume":"7","author":"F Rinaldi","year":"2007","unstructured":"Rinaldi F, Schneider G, Kaljurand K, Hess M, Romacker M: An environment for relation mining over richly annotated corpora: the case of GENIA. BMC Bioinformatics 2007, 7(Suppl 3):S3-S11. 10.1186\/1471-2105-7-S3-S3","journal-title":"BMC Bioinformatics"},{"key":"3133_CR38","unstructured":"The GENETAG corpus[\n                    ftp:\/\/ftp.ncbi.nlm.nih.gov\/pub\/tanabe\/GENETAG.tar.gz\n                    \n                  ]"},{"key":"3133_CR39","unstructured":"BioCreAtIvE - Critical Assessment for Information Extraction in Biology[\n                    http:\/\/biocreative.sourceforge.net\/\n                    \n                  ]"},{"key":"3133_CR40","unstructured":"The AIMed corpus[\n                    ftp:\/\/ftp.cs.utexas.edu\/pub\/mooney\/bio-data\/interactions.tar.gz\n                    \n                  ]"},{"key":"3133_CR41","unstructured":"Databese of Interacting Proteins[\n                    http:\/\/dip.doe-mbi.ucla.edu\/\n                    \n                  ]"},{"key":"3133_CR42","first-page":"209","volume-title":"Proceedings of the workshop of the 45th Annual Meeting of the Association for Computational Linguistics: 23-30 June 2007; Prague, Czech Republic","author":"K Yoshida","year":"2007","unstructured":"Yoshida K, Tsujii J: Reranking for biomedical named-entity recognition. Proceedings of the workshop of the 45th Annual Meeting of the Association for Computational Linguistics: 23\u201330 June 2007; Prague, Czech Republic 2007, 209\u2013216."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-10-403.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-10-403\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-10-403.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,23]],"date-time":"2019-01-23T07:04:49Z","timestamp":1548227089000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-10-403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,12]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2009,12]]}},"alternative-id":["3133"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-10-403","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,12]]},"article-number":"403"}}