ParaMT: a Paraphraser for Machine Translation

Abstract

In this paper we present ParaMT, a bilingual/multilingual paraphraser to be applied in machine translation. We select paraphrases of support verb constructions and use the NooJ linguistic environment to formalize and generate translation equivalences through the use of dictionary and local grammars with syntactic and semantic content. Our research shows that linguistic paraphrasal knowledge constitutes a key element in conversion of source language into controlled language text that presents more successful translation results