Combining Multiple Resources to Improve SMT-based Paraphrasing Model

This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and a feature function are derived from each resource, which are then combined in a log-linear SMT model for sentence-level paraphrase generation. Experimental results show that the SMT-based paraphrasing model can be enhanced using multiple resources. The phrase-level and sentence-level precision of the generated paraphrases are above 60% and 55%, respectively. In addition, the contribution of each resource is evaluated, which indicates that all the exploited resources are useful for generating paraphrases of high quality.

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: Shiqi Zhao, Cheng Niu, Ming Zhou, Ting Liu, Sheng Li
• Keywords: ACL 2008, Computational Linguistics, Multiple Resources, Paraphrases, Phrasal Paraphrase Table