German has a richer system of inflectional morphology than English, which causes problems for current approaches to statistical word alignment. Using Giza++ as a reference implemen...
We propose a backoff model for phrasebased machine translation that translates unseen word forms in foreign-language text by hierarchical morphological abstractions at the word an...
We propose an unsupervised approach utilizing only raw corpora to enhance morphological alignment involving highly inflected languages. Our method focuses on closed-class morpheme...
We improve the quality of statistical machine translation (SMT) by applying models that predict word forms from their stems using extensive morphological and syntactic information...
Abstract. German compound words pose special problems to statistical machine translation systems: the occurence of each of the components in the training data is not sufficient for...