Comparing Phrase-based and Syntax-based Paraphrase Generation
Sander Wubben, Erwin Marsi, Antal P. J. van den Bosch, Emiel Krahmer · 2011
Paraphrase generation can be regarded as machine translation where source and target language are the same. We use the Moses statistical machine translation toolkit for paraphrasing, comparing phrase-based to syntax-based approaches. Data is derived from a recently released, large scale (2.1M tokens) paraphrase corpus for Dutch. Preliminary results indicate that the phrase-based approach performs better in terms of NIST scores and produces paraphrases at a greater distance from the source. 1