@Note: a workbench for biomedical text mining. Export

@article{LourencoCCGFFRR09, abstract = {Biomedical Text Mining (BioTM) is providing valuable approaches to the automated curation of scientific literature. However, most efforts have addressed the benchmarking of new algorithms rather than user operational needs. Bridging the gap between BioTM researchers and biologists' needs is crucial to solve real-world problems and promote further research. We present @Note, a platform for BioTM that aims at the effective translation of the advances between three distinct classes of users: biologists, text miners and software developers. Its main functional contributions are the ability to process abstracts and full-texts; an information retrieval module enabling PubMed search and journal crawling; a pre-processing module with PDF-to-text conversion, tokenisation and stopword removal; a semantic annotation schema; a lexicon-based annotator; a user-friendly annotation view that allows to correct annotations and a Text Mining Module supporting dataset preparation and algorithm evaluation. @Note improves the interoperability, modularity and flexibility when integrating in-home and open-source third-party components. Its component-based architecture allows the rapid development of new applications, emphasizing the principles of transparency and simplicity of use. Although it is still on-going, it has already allowed the development of applications that are currently being used.}, author = {Louren\c{c}o, An\'{a}lia and Carreira, Rafael and Carneiro, S\'{o}nia and Maia, Paulo and Glez-Pe\~{n}a, Daniel and Fdez-Riverola, Florentino and Ferreira, Eug\'{e}nio C. and Rocha, Isabel and Rocha, Miguel}, citeulike-article-id = {4406461}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.jbi.2009.04.002}, citeulike-linkout-1 = {http://linkinghub.elsevier.com/retrieve/pii/S1532046409000537}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/19393341}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=19393341}, day = {22}, doi = {10.1016/j.jbi.2009.04.002}, issn = {1532-0480}, journal = {Journal of biomedical informatics}, keywords = {annotation, biomedical, component-based, curation, development, entity, extraction, information, literature, mining, named, recognition, retrieval, semantic, software, text}, month = {August}, number = {4}, pages = {710--720}, posted-at = {2009-07-27 14:28:36}, priority = {2}, title = {@Note: a workbench for biomedical text mining.}, url = {http://dx.doi.org/10.1016/j.jbi.2009.04.002}, volume = {42}, year = {2009} }

TY - JOUR ID - LourencoCCGFFRR09 L3 - citeulike-article-id:4406461 N2 - Biomedical Text Mining (BioTM) is providing valuable approaches to the automated curation of scientific literature. However, most efforts have addressed the benchmarking of new algorithms rather than user operational needs. Bridging the gap between BioTM researchers and biologists' needs is crucial to solve real-world problems and promote further research. We present @Note, a platform for BioTM that aims at the effective translation of the advances between three distinct classes of users: biologists, text miners and software developers. Its main functional contributions are the ability to process abstracts and full-texts; an information retrieval module enabling PubMed search and journal crawling; a pre-processing module with PDF-to-text conversion, tokenisation and stopword removal; a semantic annotation schema; a lexicon-based annotator; a user-friendly annotation view that allows to correct annotations and a Text Mining Module supporting dataset preparation and algorithm evaluation. @Note improves the interoperability, modularity and flexibility when integrating in-home and open-source third-party components. Its component-based architecture allows the rapid development of new applications, emphasizing the principles of transparency and simplicity of use. Although it is still on-going, it has already allowed the development of applications that are currently being used. IS - 4 JF - Journal of biomedical informatics SN - 1532-0480 EP - 720 TI - @Note: a workbench for biomedical text mining. VL - 42 SP - 710 KW - annotation KW - biomedical KW - component-based KW - curation KW - development KW - entity KW - extraction KW - information KW - literature KW - mining KW - named KW - recognition KW - retrieval KW - semantic KW - software KW - text AU - Lourenço, Anália AU - Carreira, Rafael AU - Carneiro, Sónia AU - Maia, Paulo AU - Glez-Peña, Daniel AU - Fdez-Riverola, Florentino AU - Ferreira, Eugénio AU - Rocha, Isabel AU - Rocha, Miguel PY - 2009/08/22/ UR - http://dx.doi.org/10.1016/j.jbi.2009.04.002 ER -