A model of co-occurrence in bitext is a boolean predicate that indicates whether a given pair of word tokens co-occur in corresponding regions of the bitext space. Co-occurrence i...
We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the b...
In this paper we use statistical machine translation and morphology information from two different morphological analyzers to try to improve translation quality by linguistically ...
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
Hierarchical phrase-based models provide a powerful mechanism to capture non-local phrase reorderings for statistical machine translation (SMT). However, many phrase reorderings a...