Empirical data on corpus design and usage in biomedical natural language processing. Export

@article{citeulike:938277, abstract = {This paper describes the design of six publicly available biomedical corpora. We then present usage data for the six corpora. We show that corpora that are carefully annotated with respect to structural and linguistic characteristics and that are distributed in standard formats are more widely used than corpora that are not. These findings have implications for the design of the next generation of biomedical corpora.}, address = {Center for Computational Pharmacology, U. of Colorado School of Medicine, USA. kevin.cohen@gmail.com}, author = {Cohen, K. B. and Fox, L. and Ogren, P. V. and Hunter, L.}, citeulike-article-id = {938277}, citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/16779021}, citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=16779021}, howpublished = {In the AMIA Proceedings CD}, issn = {1559-4076}, journal = {AMIA Annu Symp Proc}, keywords = {corpus, design, evaluation, language, natural, nlp, processing}, pages = {156--160}, posted-at = {2007-01-23 18:32:00}, priority = {0}, title = {Empirical data on corpus design and usage in biomedical natural language processing.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/16779021}, year = {2005} }

TY - JOUR ID - citeulike:938277 L3 - citeulike-article-id:938277 N2 - This paper describes the design of six publicly available biomedical corpora. We then present usage data for the six corpora. We show that corpora that are carefully annotated with respect to structural and linguistic characteristics and that are distributed in standard formats are more widely used than corpora that are not. These findings have implications for the design of the next generation of biomedical corpora. JF - AMIA Annu Symp Proc SN - 1559-4076 AD - Center for Computational Pharmacology, U. of Colorado School of Medicine, USA. kevin.cohen@gmail.com EP - 160 TI - Empirical data on corpus design and usage in biomedical natural language processing. SP - 156 KW - corpus KW - design KW - evaluation KW - language KW - natural KW - nlp KW - processing AU - Cohen, KB AU - Fox, L AU - Ogren, PV AU - Hunter, L PY - 2005/// UR - http://view.ncbi.nlm.nih.gov/pubmed/16779021 ER -