Most distributed real-time embedded systems are specified combining state diagram and data flow languages. This leads to several real-time codes which together do not necessaril...
This paper explores the feasibility of a multilingual question answering approach based on the Web redundancy. The paper introduces a system prototype that combines a translation m...
In prior work, we have proposed techniques to extend the ease of shared-memory parallel programming to distributed-memory platforms by automatic translation of OpenMP programs to ...
Minimum Error Rate Training (MERT) and Minimum Bayes-Risk (MBR) decoding are used in most current state-of-theart Statistical Machine Translation (SMT) systems. The algorithms wer...
Shankar Kumar, Wolfgang Macherey, Chris Dyer, Fran...
One style of Multi-Engine Machine Translation architecture involves choosing the best of a set of outputs from different systems. Choosing the best translation from an arbitrary s...