Distributed modules for text annotation and IE applied to the biomedical domain

@article{Kirsch2006, abstract = {SummaryBiological databases contain facts from scientific literature that have been curated by hand to ensure high quality. Curation is time-consuming and can be supported by information extraction methods. We present a server software infrastructure which allows to easily plug in modules to identify biologically interesting pieces of text to be then presented in a web interface to the curator. There are modules which identify UniProt, UMLS and GO terminology, gene and protein names, mutations and protein-protein interactions. UniProt, UMLS and GO concepts are automatically linked to the original source. The module for mutations is based on syntax patterns and the one for protein-protein interactions relies on chunk parsing. All modules work as separate servers possibly distributed on different machines and can be combined into processing pipelines as necessary. Communication is based on XML annotated text streams, each server processing the XML elements it is designed for, and possibly adding more information in the form of XML annotation. The server and the underlying software are available to the public.}, author = {Kirsch, Harald and Gaudan, Sylvain and Rebholz-Schuhmann, Dietrich }, citeulike-article-id = {348519}, doi = {http://dx.doi.org/10.1016/j.ijmedinf.2005.06.011}, journal = {International Journal of Medical Informatics}, keywords = {component, ie, java, module, ner, textmining}, posted-at = {2008-04-23 10:30:26}, priority = {2}, title = {Distributed modules for text annotation and IE applied to the biomedical domain}, url = {http://dx.doi.org/10.1016/j.ijmedinf.2005.06.011}, volume = {In Press, Corrected Proof} }

TY - JOUR ID - Kirsch2006 L3 - citeulike-article-id:348519 TI - Distributed modules for text annotation and IE applied to the biomedical domain JF - International Journal of Medical Informatics VL - In Press, Corrected Proof N2 - SummaryBiological databases contain facts from scientific literature that have been curated by hand to ensure high quality. Curation is time-consuming and can be supported by information extraction methods. We present a server software infrastructure which allows to easily plug in modules to identify biologically interesting pieces of text to be then presented in a web interface to the curator. There are modules which identify UniProt, UMLS and GO terminology, gene and protein names, mutations and protein-protein interactions. UniProt, UMLS and GO concepts are automatically linked to the original source. The module for mutations is based on syntax patterns and the one for protein-protein interactions relies on chunk parsing. All modules work as separate servers possibly distributed on different machines and can be combined into processing pipelines as necessary. Communication is based on XML annotated text streams, each server processing the XML elements it is designed for, and possibly adding more information in the form of XML annotation. The server and the underlying software are available to the public. KW - component KW - ie KW - java KW - module KW - ner KW - textmining AU - Kirsch, Harald AU - Gaudan, Sylvain AU - Rebholz-Schuhmann, Dietrich UR - http://dx.doi.org/10.1016/j.ijmedinf.2005.06.011 ER -