In this paper we show how to train statistical machine translation systems on reallife tasks using only non-parallel monolingual data from two languages. We present a modificatio...
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...
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...
The hierarchical Pitman-Yor process-based smoothing method applied to language model was proposed by Goldwater and by Teh; the performance of this smoothing method is shown compara...
Training a statistical machine translation starts with tokenizing a parallel corpus. Some languages such as Chinese do not incorporate spacing in their writing system, which creat...