Extracting Entities and Relations in Portuguese Documents - Natalie Vargas (Accenture)
Analyzing text documents can be a time consuming and sometimes repetitive task. This talk describes an application developed to interpret these documents, extracting important information. A pipeline of machine learning models comprising Named-Entity Recognition and Relation Extraction approaches was constructed in order to address the individual problems that compose this task. We have applied our method in Letters of Attorney and Articles of Incorporation (juridical domain).
Natalie Vargas is currently analyst working with Machine Learning and Natural Language processing in applications. I have been working with machine learning techniques in order to come up with solutions for documents identification and relation. I have a bachelor's degree in Computer Science with a period abroad as part of my degree, and I am currently finishing my master degree in Computer Science, focused on Computational Linguistics.