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...
We describe a new approach to SMT adaptation that weights out-of-domain phrase pairs according to their relevance to the target domain, determined by both how similar to it they a...
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...
We present two methods for estimating replacement probabilities without using parallel corpora. The first method proposed exploits the possible translation probabilities latent in ...
We introduce a semi-supervised approach to training for statistical machine translation that alternates the traditional Expectation Maximization step that is applied on a large tr...