Improving a Catalan-Spanish statistical translation system using morphosyntactic knowledge

Comunicació presentada a la 13th Annual Conference of the European Association for Machine Translation, celebrada a Barcelona (Espanya) els dies 14 i 15 de maig del 2009.In this paper, a human evaluation of a Catalan-Spanish Ngram-based statistical machine translation system is used to develop specific techniques based on the use of grammatical categories, lexical categorisation and text processing, for the enhancement of the final translation. The system is successfully improved when testing with ad hoc and general corpora, as it is shown in the final automatic evaluation