Abstract Machine translation (MT) is-not only historically-a prime application of language
technology. After years of seeming stagnation, the price pressure on language service …

The objective of this thesis is to directly incorporate comparable corpora into the estimation
of end-to-end statistical machine translation (SMT) models. Typically, SMT models are …

Abstract Machine translation (MT) evaluation metrics based on n-gram co-occurrence
statistics are financially cheap to execute and their value in comparative research is well …

Virtually all human communication that portrays an event or sequence of events is framed as
a narrative, from films, novels, and news reports to clinical notes, legal briefs, gossip, and …

The aim of the thesis is to explore methods of machine translation when translating between
languages with significant differences in word order and in the direction to the …

Previously, statistical machine translation (SMT) models have been estimated from parallel
corpora, or pairs of translated sentences. In this thesis, we directly incorporate comparable …

Bilingual corpora constitute an indispensable resource for translation model training in
statistical machine translation. However, it is not really clear if including all the training data …

Modern machine translation techniques typically incorporate both a translation model, which
guides how individual words and phrases can be translated, and a language model (LM) …

The aim of this thesis is to express fundamentals and concepts behind one of the emerging
techniques in statistical machine translation (SMT)-hierarchical phrase based MT by …

A breakthrough in Machine Translation is only possible if human translators are taken into
the loop. While mechanisms for automatic evaluation and scoring such as BLEU have …