Measuring the Performance of a Location-Aware Text Prediction System

Abstract

In recent years, some works have discussed the conception of location-aware Augmentative and Alternative Communication (AAC) systems with very positive feedback from participants. However, in most cases, complementary quantitative evaluations have not been carried out to confirm those results. To contribute to clarifying the validity of these approaches, our study quantitatively evaluated the effect of using language models with location knowledge on the efficiency of a word and sentence prediction system. Using corpora collected for three different locations (classroom, school cafeteria, home), location-specific language models were trained with sentences from each location and compared with a traditional all-purpose language model, trained on all corpora. User tests showed a modest mean improvement of 2.4% and 1.3% for Words Per Minute (WPM) and Keystroke Saving Rate (KSR), respectively, but the differences were not statistically significant. Since our text prediction system relies on the concept of sentence reuse, we ran a set of simulations with language models having different sentence knowledge levels (0%, 25%, 50%, 75%, 100%). We also introduced in the comparison a second location-aware strategy that combines the location-specific approach with the allpurpose approach (mixed approach). The mixed language models performed better under low sentence-reuse conditions (0%, 25%, 50%) with 1.0%, 1.3%, and 1.2% KSR improvements, respectively. The location-specific language models performed better under high sentence-reuse conditions (75%, 100%) with 1.7% and 1.5% KSR improvements, respectively.

Predictive composition of pictogram messages for users with autism

“…Text prediction methods are the most extended techniques to improve the rate of communication for people who use Augmentative and Alternative Communication systems due to any kind of motor or speech impairments (Garay-Vitoria and Abascal 2006). These methods range from word prediction (Koester and Levine 1996;Venkatagiri 1993;Magnuson and Hunnicutt 2002;Pouplin et al 2014) to sentence prediction (Arnott et al 1992;Garay-Vitoria et al 1995;Mitchell and Sproat 2012;Garcia et al 2014), through the use of n-grams (Wiegand and Patel 2012), topic modeling (Trnka et al 2006) or context-awareness (Higginbotham et al 2009;Garcia et al 2015) as base of the prediction algorithms.…”