In this paper we propose an approach to corpus-based generation in a machine translation framework that ia aimilar to shake&bake. A bag of words is mapped against an automatically induced target language template grammar and a sentense is generated by recursively applying rules that are exracted from the template grammar. We show how we induce a tempaltegrammar and how it can be enriched with additional paraphasing knowledge. We suggest a framework for weighting and training the template grammar and show that the enriched template grammar produce better paraphrases.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.