Unlike traditional classification tasks, multilabel classification allows a sample to associate with more than one label. This generalization naturally arises the difficulty in cla...
We present new results from a real-user evaluation of a data-driven approach to learning user-adaptive referring expression generation (REG) policies for spoken dialogue systems. ...
Abstract. Current Learning Management Systems were typically conceived to offer a self-contained "one size fits all" learning environment. Adaptive educational systems ha...
In this paper, we propose a cross-layer design (CLD) scheme combining rate adaptation and four types of hybrid automatic repeat request (HARQ) for multiband orthogonal frequency di...
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...