Structuring Medical Records with Apache Stanbol – Rafa Haro, Athento & Antonio David Perez Morales
Apache Stanbol (https://stanbol.apache.org) is a top level Apache project which main objective is to provide a set of reusable components for semantic content management. Built from a extremely modular point of view, Stanbol is an OSGi based framework that uses a number of Apache tools like Solr, Felix, OpenNLP, Clerezza, Tika, Sling and Jena.
The intention of this talk is double. On one hand, we will offer a detailed overview of the current situation of the project, from the technical and community point of view. On the other hand, we will showcase a real use case where Stanbol is being used for structuring text medical records in several languages. Through this real use case explanation, we will be exposing how Stanbol can be used for things like: processing multi-language text, use semantic datasets for Content Enhancement and NLP tasks like Fact Extraction and Negation Detection