The language component of the FASTY predictive typing system

Abstract

I describe the language component of FASTY, a text prediction system designed to improve text input efficiency for disabled users. The FASTY language component is based on state-of-the-art n-gram-based word-level and Part-of-Speech-level prediction and on a number of innovative modules (morphological analysis, collocation-based prediction, compound prediction) that are meant to enhance performance in languages other
than English. Together with its modular architecture these novel techniques make it adaptable to a wide range of languages without sacrificing performance.  Currently, versions for Dutch, German, French, Italian, and Swedish are supported.
Going beyond the FASTY system, it will also be shown that the language component can be easily extended for the use with reduced keyboards, just by defining key-mapping tables, without needing to change the dictionary or the language model.