Title: Uma arquitetura de question-answering instanciada no domínio de doenças crônicas
Abstract: The medical record describes health conditions of patients helping experts to make decisions about the treatment.The biomedical scientific knowledge can improve the prevention and the treatment of diseases.However, the search for relevant knowledge may be a hard task because it is necessary time and the healthcare research is constantly updating.Many healthcare professionals have a stressful routine, because they work in different hospitals or medical offices, taking care many patients per day.The goal of this project is to design a Question Answering Framework to support faster and more precise searches for information in epigenetic, chronic disease and thyroid images.To develop the proposal, we are reusing two frameworks that have already developed: SisViDAS and FREDS.These two frameworks are being exploited to compose a document processing module.The other modules (question and answer processing) are being completely developed.The QASF was evaluated by a reference collection and performance measures.The results show 0, 7 of precision and 0, 3 of recall for two hundred articles retrieved.Considering that the questions inserted on the framework have an average of seventy terms, the QASF shows good results.This project intends to decrease search time once QA systems provide straight and precise answers in a process started by a user question in natural language.