Development of an augmentative and alternative communication app for the Maltese language

Abstract

Augmentative and Alternative Communication (AAC) embodies all methods of communication, serving to augment or function as an alternative to speech. Maltese children having complex communication needs use various AAC devices on a daily basis. Their conversation skills are mainly limited by two key factors. The fact that AAC users communicate up to 20 times slower than those who use regular speech is the first of these two limiting factors. The second one is the unavailability of an AAC app for the Maltese language. This paper presents the development of an AAC app targeted for the Maltese language, which provides an intelligent word suggestion mechanism to improve AAC rates. The app is based on a trigram language model which is able to predict the subsequent word by considering the previous two. The model was trained by means of a specifically created corpus and uses the Interpolated Kneser-Ney Smoothing technique to correctly resolve contexts which were not observed during training. The app enables users to retrain and update the language model, such that it may provide additional personalised word suggestions. The app was evaluated by a number of clinicians and educators who regularly work with AAC users. They remarked that it will be potentially helpful in aiding Maltese children during intervention sessions in view of its effective features. The underlying language model features an average perplexity of 90.47 when tested with non-similar training and test data and an average perplexity of 3.61 when evaluated for highly similar training and test data. The low perplexity values suggest that the language model employed in this app is remarkably accurate and is effectively performing as other trigram language models reported in the literature.