3 Julho 2017, 17:42 - Fátima Sampaio
Candidate: Luís Filipe Nobre Horta Baptista Garcia N.º 60957/D
Title: Toward a Context-Aware Augmentative and Alternative Communication System with Vocabulary Prediction for the European Portuguese
Location: Sala 0.20, INESC-ID
Advisors: Professor Luís Miguel Veiga Vaz Caldas de Oliveira / Professor David Manuel Martins de Matos
Abstract: Persons who rely on Augmentative and Alternative Communication (AAC) systems to communicate, face many difficulties when they try to maintain a dialog, in part because of the poor output rates offered by current systems. To minimize this problem, in this PhD we propose applying the whole utterance approach to vocabulary prediction. One of the techniques we propose to study is sentence prediction, a technique that may complement word prediction to assist users compose their messages faster. We are also interested in studying counterpart techniques for AAC users who communicate with pictograms, namely single pictogram prediction and pictogram sentence prediction. In addition, since prediction of sentences seems to be a very context-dependent process, we also propose to evaluate use of context-awareness to improve prediction results. To test this approach we created several real AAC solutions with the collaboration of rehabilitation professionals. Results from user tests, and software emulations, carried out until the present moment, showed interesting improvements in words per minute and keystroke savings.