Paraphrase Recognition via Dissimilarity Significance Classification

We propose a supervised, two-phase framework to address the problem of paraphrase recognition (PR). Unlike most PR systems that focus on sentence similarity, our framework detects dissimilarities between sentences and makes its paraphrase judgment based on the significance of such dissimilarities. The ability to differentiate significant dissimilarities not only reveals what makes two sentences a nonparaphrase, but also helps to recall additional paraphrases that contain extra but insignificant information. Experimental results show that while being accurate at discerning non-paraphrasing dissimilarities, our implemented system is able to achieve higher paraphrase recall (93%), at an overall performance comparable to the alternatives.

• Type: Conference
• Year: 2006
• Where: EMNLP
• Authors: Long Qiu, Min-Yen Kan, Tat-Seng Chua
• Keywords: EMNLP 2006, EMNLP 2007, Framework Detects Dissimilarities, Paraphrase, Significant Dissimilarities