We investigate the use of Fisher's exact significance test for pruning the translation table of a hierarchical phrase-based statistical machine translation system. In additio...
We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
Given several systems' automatic translations of the same sentence, we show how to combine them into a confusion network, whose various paths represent composite translations...
Damianos Karakos, Jason Eisner, Sanjeev Khudanpur,...
We present cdec, an open source framework for decoding, aligning with, and training a number of statistical machine translation models, including word-based models, phrase-based m...
Chris Dyer, Adam Lopez, Juri Ganitkevitch, Jonatha...
Partitioning is a time consuming and computationally complex optimization problem in the codesign of hardware software systems. The stringent time-to-market requirements have resu...