Videotext recognition is challenging due to low resolution, diverse fonts/styles, and cluttered background. Past methods enhanced recognition by using multiple frame averaging, im...
This paper introduces new methods based on exponential families for modeling the correlations between words in text and speech. While previous work assumed the effects of word co-...
The seemingly simple choice of whether to use call variance or call subsumption in a tabled evaluation deeply affects an evaluation’s properties. Most tabling implementations hav...
The rate of occurrence of words is not uniform but varies from document to document. Despite this observation, parameters for conventional n-gram language models are usually deriv...
Parallel programming models based on a mixture of task and data parallelism have shown to be successful in addressing the increasing communication overhead of distributed memory p...