Exploring Medical Records with Machine Learning and Natural Language Processing

3 April 2018

Pedro Balage and Pedro Mendes Priberam

We will present an ongoing project at Priberam that covers aspects that go from the definition of ontologies, corpus gathering and annotation criteria to the concrete annotation task, and finally the development of an engine that automatically extracts, labels and enables the exploration of textual data obtained from medical records. We will report on the resulting nested named-entity recognizer based on stack-LSTMs that achieved state-of-the-art results in standard evaluation datasets.



Pedro Balage holds a PhD in computer science (2017) from University of São Paulo, with background in computational linguistics (MA) and computer science (BSc). He has been working in the field of Natural Language Processing for about 8 years, of which 2 years as research scientist at Priberam. Pedro Mendes started his lexicographer career 18 years ago in Academia das Ciências de Lisboa and has been working in the field of computational linguistics for the last 15 years as part of the linguistics department in Priberam.