Learning transfer rules for machine translation from parallel corpora

In this paper we present JETCAT, a Japanese-English transfer-based machine translation system. Our main research contribution is that the transfer rules are not handcrafted but are learnt automatically from a parallel corpus. The system has been implemented in Amzi! Prolog, which offers scalability for large rule bases, full Unicode support for Japanese characters, and several APIs for the seamless integration of the translation functionality into common office environments. As a first user interface we have developed a translation environment under Microsoft Word. The dynamic nature of our system allows for an easy customization of the rule base according to the user's personal preferences by simply post-editing the translation results, which leads to an automatic update. The user interface for Microsoft Word also provides the possibility for the user to display token lists, parse trees, and transfer rules, which makes JETCAT also a very useful tool for language students.