Monolingual Machine Translation for Paraphrase Generation

We apply statistical machine translation (SMT) tools to generate novel paraphrases of input sentences in the same language. The system is trained on large volumes of sentence pairs automatically extracted from clustered news articles available on the World Wide Web. Alignment Error Rate (AER) is measured to gauge the quality of the resulting corpus. A monotone phrasal decoder generates contextual replacements. Human evaluation shows that this system outperforms baseline paraphrase generation techniques and, in a departure from previous work, offers better coverage and scalability than the current best-of-breed paraphrasing approaches.

• Type: Conference
• Year: 2004
• Where: EMNLP
• Authors: Chris Quirk, Chris Brockett, William B. Dolan
• Keywords: Alignment Error Rate, Baseline Paraphrase Generation, EMNLP 2004, EMNLP 2007, Monotone Phrasal Decoder