A combination of rule and supervised learning approach to recognize paraphrases

Paraphrase recognition is the basic of paraphrase researches. However, most of the existing researches mainly focus on the acquirement of paraphrases from a certain text corpus, or their methods are restricted to certain conditions. There is not a method that can decide whether two sentences are paraphrases generally. This paper presents a combination of rule and supervised learning method to recognize paraphrases. In this method, we make use of the classification of paraphrases and adopt different approaches to recognize paraphrases according to the types they belong to. And the key point is how to use a variety of strategies to get the semantic similarity of two sentences. As the system is mainly for question answering (QA), evaluations are conducted on a corpus of sentence pairs mainly collected from a QA system, Baidu zhidao. Results show that the precision exceeds 75% on the simple sentences whose syntax analyses are correct, which is significantly higher than most of the existing methods.