This paper presents a novel training algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the global scoring...
In Chinese texts, words composed of single or multiple characters are not separated by spaces, unlike most western languages. Therefore Chinese word segmentation is considered an ...
An unsupervised discriminative training procedure is proposed for estimating a language model (LM) for machine translation (MT). An English-to-English synchronous context-free gra...
Zhifei Li, Ziyuan Wang, Sanjeev Khudanpur, Jason E...
Abstract. This paper describes an example-based machine translation (EBMT) method based on tree-string correspondence (TSC) and statistical generation. In this method, the translat...
We describe a novel approach to machine translation that combines the strengths of the two leading corpus-based approaches: Phrasal SMT and EBMT. We use a syntactically informed d...