Paraphrase Generation as Monolingual Translation: Data and Evaluation

In this paper we investigate the automatic generation and evaluation of sentential paraphrases. We describe a method for generating sentential paraphrases by using a large aligned monolingual corpus of news headlines acquired automatically from Google News and a standard Phrase-Based Machine Translation (PBMT) framework. The output of this system is compared to a word substitution baseline. Human judges prefer the PBMT paraphrasing system over the word substitution system. We demonstrate that BLEU correlates well with human judgements provided that the generated paraphrased sentence is sufficiently different from the source sentence.

• Type: Journal
• Year: 2010
• Where: INLG
• Authors: Sander Wubben, Antal van den Bosch, Emiel Krahmer
• Keywords: INLG 2010, Natural Language Processing, Sentential Paraphrases, Word Substitution, Word Substitution Baseline