Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...
This paper addresses the problem of synchronizing movie subtitles, which is necessary to improve alignment quality when building a parallel corpus out of translated subtitles. In ...
In recent years, corpus based approaches to machine translation have become predominant, with Statistical Machine Translation (SMT) being the most actively progressing area. Succe...
In this paper we address the problem of translating between languages with word order disparity. The idea of augmenting statistical machine translation (SMT) by using a syntax-bas...
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...