Recent advances on language based software toolkit generation enables performance driven exploration of embedded systems by exploiting the application behavior. There is a need fo...
We explore morphology-based and sub-word language modeling approaches proposed for morphologically rich languages, and evaluate and contrast them for Turkish broadcast news transc...
Lasso is a regularization method for parameter estimation in linear models. It optimizes the model parameters with respect to a loss function subject to model complexities. This p...
This paper presents the cache configuration exploration of a programmable system, in order to find the best matching between the architecture and a given application. Here, prog...
Pablo Viana, Edna Barros, Sandro Rigo, Rodolfo Aze...
Many reordering approaches have been proposed for the statistical machine translation (SMT) system. However, the information about the type of source sentence is ignored in the pr...