Compositional Language Modeling for Icon-Based Augmentative and Alternative Communication
Overview
Authors
Affiliations
Icon-based communication systems are widely used in the field of Augmentative and Alternative Communication. Typically, icon-based systems have lagged behind word- and character-based systems in terms of predictive typing functionality, due to the challenges inherent to training icon-based language models. We propose a method for synthesizing training data for use in icon-based language models, and explore two different modeling strategies.
AAC and Artificial Intelligence (AI).
Sennott S, Akagi L, Lee M, Rhodes A Top Lang Disord. 2021; 39(4):389-403.
PMID: 34012187 PMC: 8130588. DOI: 10.1097/tld.0000000000000197.
Huggins J, Guger C, Aarnoutse E, Allison B, Anderson C, Bedrick S Brain Comput Interfaces (Abingdon). 2020; 6(3):71-101.
PMID: 33033729 PMC: 7539697. DOI: 10.1080/2326263X.2019.1697163.