no code implementations • 23 Jul 2018 • Karan Aggarwal, Swaraj Khadanga, Shafiq R. Joty, Louis Kazaglis, Jaideep Srivastava
We propose an end-to-end framework that uses a combination of deep convolution and recurrent neural networks to extract high-level features from raw flow signal with a structured output layer based on a conditional random field to model the temporal transition structure of the sleep stages.
no code implementations • 5 Oct 2017 • Francisco Guzmán, Shafiq R. Joty, Lluís Màrquez, Preslav Nakov
We present a framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation.