In language modeling for speech recognition, both the amount of training data and the match to the target task impact the goodness of the model, with the trade-off usually favorin...
Marius A. Marin, Sergey Feldman, Mari Ostendorf, M...
This paper presents a soft-typing system for the programming language Erlang. The system is based on two concepts; a (forward) data flow analysis that determines upper approximat...
Because uncertain reasoning is often intractable, it is hard to reason with a large amount of knowledge. One solution to this problem is to specify a set of possible models, some s...
Charles A. Sutton, Brendan Burns, Clayton T. Morri...
Feature selection is very important for many computer vision applications. However, it is hard to find a good measure for the comparison. In this study, feature sets are compared ...
Program traces can be used to drive visualisations of reusable components, but such traces can be gigabytes in size, are very expensive to generate, and are hard to extract inform...
Craig Anslow, Stuart Marshall, Robert Biddle, Jame...