CONF VILLATORO-TELLO_IBERIANLANGUAGESEVALUATIONFORUM(IBERLEF2020)_2020/IDIAP Idiap and UAM Participation at MEX-A3T Evaluation Campaign Villatoro-Tello, Esaú Ramírez-de-la-Rosa, Gabriela Parida, Shantipriya Kumar, Sajit Motlicek, Petr deep learning Natural language processing Supervised Autoencoders Text Representation EXTERNAL https://publications.idiap.ch/attachments/papers/2021/VILLATORO-TELLO_IBERIANLANGUAGESEVALUATIONFORUM(IBERLEF2020)_2020.pdf PUBLIC Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2020) co-located with 36th Conference of the Spanish Society for Natural Language Processing (SEPLN 2020) 2664 6 1613-0073 2020 CEUR Workshop Proceedings http://ceur-ws.org/Vol-2664/mexa3t_paper3.pdf URL This paper describes our participation in the shared evaluation campaign of MexA3T 2020. Our main goal wasto evaluate a Supervised Autoencoder (SAE) learning algorithm in text classification tasks. For our experiments,we used three different sets of features as inputs, namely classic word n-grams, char n-grams, and Spanish BERTencodings. Our results indicate that SAE is adequate for longer and more formal written texts. Accordingly,our approach obtained the best performance (