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

Authors:
Carrie Demmans Epp;Justin Djordjevic;Shimu Wu;Karyn Moffatt;Ronald M. Baecker
Affiliations:
Dept. of Computer Science, University of Toronto, Toronto, Ontario, Canada;Dept. of Computer Science, University of Toronto, Toronto, Ontario, Canada;Dept. of Computer Science, University of Toronto, Toronto, Ontario, Canada;School of Information Studies, McGill University, Montreal, Quebec, Canada;Dept. of Computer Science, University of Toronto, Toronto, Ontario, Canada
Venue:
Proceedings of the 2012 ACM international conference on Intelligent User Interfaces
Year:
2012

Citing 6
Cited 0

Introduction to Modern Information Retrieval

Introduction to Modern Information Retrieval
The rôle of natural language processing in alternative and augmentative communication

Natural Language Engineering
Speech and Language Processing (2nd Edition)

Speech and Language Processing (2nd Edition)
Context-aware communication support system with pictographic cards

Proceedings of the 11th International Conference on Human-Computer Interaction with Mobile Devices and Services
Vocabulary navigation made easier

Proceedings of the 15th international conference on Intelligent user interfaces
Analysis of adjective-noun word pair extraction methods for online review summarization

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.