We present a new adaptive and energy-efficient broadcast model to support flexible responses to client queries. Clients do not have to request documents by name, since they may kno...
Feature selection, as a preprocessing step to machine learning, has been very effective in reducing dimensionality, removing irrelevant data, increasing learning accuracy, and imp...
Production of parallel training corpora for the development of statistical machine translation (SMT) systems for resource-poor languages usually requires extensive manual effort. ...
Automatic face photo-sketch recognition has important applications to law enforcement. Recent research has focused on transforming photos and sketches into the same modality for m...
In this paper, several approaches for language portability of dialogue systems are investigated with a focus on the spoken language understanding (SLU) component. We show that the...