Exploiting discourse information to identify paraphrases

作者：

Highlights：

• We show the relation between discourse units and paraphrasing.

• We propose a new method for computing text similarity based on elementary discourse units.

• We apply the method to the task of paraphrase identification.

• We achieved 93.4% accuracy in experiments conducted on the PAN corpus..

摘要

•We show the relation between discourse units and paraphrasing.•We propose a new method for computing text similarity based on elementary discourse units.•We apply the method to the task of paraphrase identification.•We achieved 93.4% accuracy in experiments conducted on the PAN corpus..

论文关键词：Paraphrase identification,Text similarity,Discourse segmentation,Elementary discourse unit,MT metric,Support vector machine

论文评审过程：Available online 24 October 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.10.018