This paper proposes to introduce a novel reordering model in the open-source Moses toolkit. The main idea is to provide weighted reordering hypotheses to the SMT decoder. These hy...
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
This paper presents a new hypothesis alignment method for combining outputs of multiple machine translation (MT) systems. An indirect hidden Markov model (IHMM) is proposed to add...
Xiaodong He, Mei Yang, Jianfeng Gao, Patrick Nguye...
Abstract: The abstract syntax and static semantics of UML, the widely-used generalpurpose graphical modeling language, have been standardized in a four-layer metamodeling framework...
This paper presents a novel online relevant set algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the glob...