Phrase sets for evaluating text entry techniques
CHI '03 Extended Abstracts on Human Factors in Computing Systems
Semantic knowledge in word completion
Proceedings of the 7th international ACM SIGACCESS conference on Computers and accessibility
Topic modeling in fringe word prediction for AAC
Proceedings of the 11th international conference on Intelligent user interfaces
Indirect text entry using one or two keys
Proceedings of the 8th international ACM SIGACCESS conference on Computers and accessibility
Sibylle, An Assistive Communication System Adapting to the Context and Its User
ACM Transactions on Accessible Computing (TACCESS)
The effects of word prediction on communication rate for AAC
NAACL-Short '07 Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers
Scaling high-order character language models to gigabytes
Software '05 Proceedings of the Workshop on Software
TextEntry '03 Proceedings of the 2003 EACL Workshop on Language Modeling for Text Entry Methods
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Systems Demonstrations
Asynchronous fixed-grid scanning with dynamic codes
SLPAT '11 Proceedings of the Second Workshop on Speech and Language Processing for Assistive Technologies
Improved inference and autotyping in EEG-based BCI typing systems
Proceedings of the 15th International ACM SIGACCESS Conference on Computers and Accessibility
Hi-index | 0.00 |
We present preliminary experiments of a binary-switch, static-grid typing interface making use of varying language model contributions. Our motivation is to quantify the degree to which language models can make the simplest scanning interfaces -- such as showing one symbol at a time rather than a scanning a grid -- competitive in terms of typing speed. We present a grid scanning method making use of optimal Huffman binary codes, and demonstrate the impact of higher order language models on its performance. We also investigate the scanning methods of highlighting just one cell in a grid at any given time or showing one symbol at a time without a grid, and show that they yield commensurate performance when using higher order n-gram models, mainly due to lower error rate and a lower rate of missed targets.