Abstract
In this paper, we propose using an University Entrance Exam (the Exame Nacional do Ensido Medio) as a proper test of success of artificial intelligence techniques, thus replacing the famous Turing Test. We argue that more importantly than measuring the ability of a system in replicating human competence, the so-called ENEM test can serve as a driver of development of new techniques. Additionally, we describe how we produced a machine-readable database of questions from previous exams, which can be used for comparing techniques for natural language processing, image processing and knowledge representation and reasoning. We then present some preliminaries to serve as baseline that are based on information retrieval techniques and Word2Vec. Experiments with previous exams show that in questions concerning Humanities and Languages these baseline methods perform in average slightly better than random guessing.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
