Text processing through Web services: Calling Whatizit

@article{citeulike:1922911, abstract = {Motivation: Text-mining (TM) solutions could turn are developing into efficient services to researchers in the biomedical research community. Such solutions have to scale with the growing number and size of resources (e.g., available controlled vocabularies), with the amount of literature to be processed (e.g., about 17 million documents in PubMed) and with the demands of the user community (e.g., different methods for fact extraction). These demands induce the development of server-based solutions that can be accessed programmatically. Whatizit is a suite of modules that analyse text for contained information, e.g. any own text documents, scientific publications or Medline abstracts. Each module identifies terms and then links them to the corresponding entries in bioinformatics databases such as UniProtKb/Swiss-Prot data entries and gene ontology concepts. Other modules identify a set of selected annotation types like the set produced by the EBIMed analysis pipeline for proteins. In the case of Medline abstracts, Whatizit offers access to EBI's inhouse installation via PMID or term query. For large quantities of own text, the server can be operated in a streaming mode. (http://www.ebi.ac.uk/webservices/whatizit) 10.1093/bioinformatics/btm557}, author = {Rebholz-Schuhmann, Dietrich and Arregui, Miguel and Gaudan, Sylvain and Kirsch, Harald and Yepes, Antonio J. }, citeulike-article-id = {1922911}, doi = {10.1093/bioinformatics/btm557}, journal = {Bioinformatics}, keywords = {medline}, month = {November}, pages = {btm557+}, posted-at = {2007-11-15 15:47:12}, priority = {2}, title = {Text processing through Web services: Calling Whatizit}, url = {http://dx.doi.org/10.1093/bioinformatics/btm557}, year = {2007} }

TY - JOUR ID - citeulike:1922911 L3 - citeulike-article-id:1922911 TI - Text processing through Web services: Calling Whatizit JF - Bioinformatics SP - btm557 N2 - Motivation: Text-mining (TM) solutions could turn are developing into efficient services to researchers in the biomedical research community. Such solutions have to scale with the growing number and size of resources (e.g., available controlled vocabularies), with the amount of literature to be processed (e.g., about 17 million documents in PubMed) and with the demands of the user community (e.g., different methods for fact extraction). These demands induce the development of server-based solutions that can be accessed programmatically. Whatizit is a suite of modules that analyse text for contained information, e.g. any own text documents, scientific publications or Medline abstracts. Each module identifies terms and then links them to the corresponding entries in bioinformatics databases such as UniProtKb/Swiss-Prot data entries and gene ontology concepts. Other modules identify a set of selected annotation types like the set produced by the EBIMed analysis pipeline for proteins. In the case of Medline abstracts, Whatizit offers access to EBI's inhouse installation via PMID or term query. For large quantities of own text, the server can be operated in a streaming mode. (http://www.ebi.ac.uk/webservices/whatizit) 10.1093/bioinformatics/btm557 KW - medline AU - Rebholz-Schuhmann, Dietrich AU - Arregui, Miguel AU - Gaudan, Sylvain AU - Kirsch, Harald AU - Yepes, Antonio PY - 2007/11/15/ UR - http://dx.doi.org/10.1093/bioinformatics/btm557 ER -