Sentence fusion is a text-to-text (revision-like) generation task which takes related sentences as input and merges these into a single output sentence. In this paper we describe our ongoing work on developing a sentence fusion module for Dutch. We propose a generalized version of alignment which not only indicates which words and phrases should be aligned but also labels these in terms of a small set of primitive semantic relations, indicating how words and phrases from the two input sentences relate to each other. It is shown that human labelers can perform this task with a high agreement (Fscore of.95). We then describe and evaluate our adaptation of an existing automatic alignment algorithm, and use the resulting alignments, plus the semantic labels, in a generalized fusion and generation algorithm. A small-scale evaluation study reveals that most of the resulting sentences are adequate to good. 1

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.