Towards providing just-in-time vocabulary support for assistive and augmentative communication.

Many people cannot communicate effectively with those around them. The causes vary but several tools and strategies can support their communication. These tools, which collectively fall under the banner of Assistive and Augmentative Communication (AAC), are rarely adaptive. Of those that are, few provide context-based or just-in-time vocabulary support to users even though the proliferation of smartphones makes this possible. To meet this need, we developed four algorithms to retrieve relevant vocabulary from Internet-based corpora. We used discourse completion tasks to evaluate each algorithm's ability to identify appropriate vocabulary across a set of specific contexts. The results indicate that our approach identifies appropriate context-specific words that complement general AAC vocabularies: when combined with a typical base vocabulary, the algorithms outperformed the support provided by the base vocabulary alone. They did this by adding small targeted vocabularies.