: In this paper, we propose a new approach to improve the translation quality by adding the Key-Words of a sentence to the parallel corpus. The main idea of the approach is to find...
In this paper we show how to train statistical machine translation systems on reallife tasks using only non-parallel monolingual data from two languages. We present a modificatio...
Handling terminology is an important matter in a translation workflow. However, current Machine Translation (MT) systems do not yet propose anything proactive upon tools which ass...
We present a joint morphological-lexical language model (JMLLM) for use in statistical machine translation (SMT) of language pairs where one or both of the languages are morpholog...
We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the b...