Recently, various synchronous grammars are proposed for syntax-based machine translation, e.g. synchronous context-free grammar and synchronous tree (sequence) substitution gramma...
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
A model for statistical ranking is a family of probability distributions whose states are orderings of a xed nite set of items. We represent the orderings as maximal chains in a ...
In this paper, we propose a novel dependency-based bracketing transduction grammar for statistical machine translation, which converts a source sentence into a target dependency t...
Jinsong Su, Yang Liu, Haitao Mi, Hongmei Zhao, Yaj...
Statistical testing has been shown to be more efficient at detecting faults in software than other methods of dynamic testing such as random and structural testing. Test data are g...