Winograd Schemas in Portuguese
Gabriela De Melo, Vinicius Imaizumi, Fábio Gagliardi Cozman · 2019
The Winograd Schema Challenge has become a common benchmark for question answering and natural language processing. The original set of Winograd Schemas was created in English; in order to stimulate the development of Natural Language Processing in Portuguese, we have developed a set of Winograd Schemas in Portuguese. We have also adapted solutions proposed for the English-based version of the challenge so as to have an initial baseline for its Portuguese-based version; to do so, we created a language model for Portuguese based on a set of Wikipedia documents.