Abstract. This paper describes an example-based machine translation (EBMT) method based on tree-string correspondence (TSC) and statistical generation. In this method, the translat...
We present a novel approach to integrate transliteration into Hindi-to-Urdu statistical machine translation. We propose two probabilistic models, based on conditional and joint pr...
Nadir Durrani, Hassan Sajjad, Alexander Fraser, He...
: The performance of a statistical machine translation (SMT) system heavily depends on the quantity and quality of the bilingual language resource. However, the pervious work mainl...
A Named Entity Recognizer (NER) generally has worse performance on machine translated text, because of the poor syntax of the MT output and other errors in the translation. As som...
In modern machine translation practice, a statistical phrasal or hierarchical translation system usually relies on a huge set of translation rules extracted from bi-lingual traini...