The impact of process variation in state of the art technology makes traditional (worst case) designs unnecessarily pessimistic, which translates to suboptimal designs in terms of...
The University of Maryland participated in the English and Czech tasks. For English, one monolingual run using only fields based on fully automatic transcription (the required con...
For many years, statistical machine translation relied on generative models to provide bilingual word alignments. In 2005, several independent efforts showed that discriminative m...
While phrase-based statistical machine translation systems currently deliver state-of-theart performance, they remain weak on word order changes. Current phrase reordering models ...
We describe a discriminatively trained sequence alignment model based on the averaged perceptron. In common with other approaches to sequence modeling using perceptrons, and in co...