Domain adaptation problem in statistical machine translation systems

Abstract

Globalization suddenly brings many people from different country to interact with each other, requiring them to be able to speak several languages. Human translators are slow and expensive, we find the necessity of developing machine translators to automatize the task. Several approaches of Machine translation have been develop by the researchers. In this work, we use the Statistical Machine Translation approach. Statistical Machine Translation systems perform poorly when applied on new domains. The domain adaptation problem has recently gained interest in Statistical Machine Translation. The basic idea is to improve the performance of the system trained and tuned with different domain than the one to be translated. This article studies different paradigms of domain adaptation. The results report improvements compared with a system trained only with in-domain data and trained with all the available data.