Recently, Machine Translation (MT) has become a quite popular technology in everyday use through Web services such as Google Translate. Although the dierent MT approaches provide good results, none of them exploit contextual information like named entity to help user comprehension. In this paper, we present NERITS, a machine translation mashup system using semantic annotation from Wikimeta. The goal of the application is to propose a cross-lingual translation by providing detailed informa- tion extracted from DBpedia about persons, locations and organizations in the mother tongue of the user. This helps at scaling the traditional multilingual task of machine translation to cross-lingual applications.

Demonstration: http://cms.unige.ch/lettres/linguistique/nebhi/nerits/