Problems Of Reusing An Existing MT System∗

This paper describes an attempt to recy-cle parts of the Czech-to-Russian ma-chine translation system (MT) in the new Czech-to-English MT system. The paper describes the overall architecture of the new system and the details of the modules which have been added. A special attention is paid to the prob-lem of named entity recognition and to the method of automatic acquisition of lexico-syntactic information for the bilingual dictionary of the system. The paper concentrates on the problems en-countered in the process of reusing ex-isting modules and their solution.