When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
Serious games are becoming a powerful tool in education. However, there are still open issues needing further research to generalize the use of videogames and game-like simulations...
Javier Torrente, Pablo Moreno-Ger, Baltasar Fern&a...
Estimating insurance premia from data is a difficult regression problem for several reasons: the large number of variables, many of which are discrete, and the very peculiar shape...
Nicolas Chapados, Yoshua Bengio, Pascal Vincent, J...
Tightly coupled parallel applications are increasingly run in Grid environments. Unfortunately, on many Grid sites the ability of machines to create or accept network connections ...
Binarization of n-ary rules is critical for the efficiency of syntactic machine translation decoding. Because the target side of a rule will generally reorder the source side, it ...