In this paper we present a new method, time-striding hidden Markov model (TSHMM), to learn from long-term motion for atomic behaviors and the statistical dependencies among them. T...
In this paper we present several extensions of MARIE1 , a freely available N-gram-based statistical machine translation (SMT) decoder. The extensions mainly consist of the ability...
We examine pooling data as a method for improving Statistical Machine Translation (SMT) quality for narrowly defined domains, such as data for a particular company or public entit...
It is possible to reduce the bulk of phrasetables for Statistical Machine Translation using a technique based on the significance testing of phrase pair co-occurrence in the para...
Howard Johnson, Joel D. Martin, George F. Foster, ...
This work presents improvements of a large-scale Arabic to French statistical machine translation system over a period of three years. The development includes better preprocessin...