Computing Paraphrasability of Syntactic Variants Using Web Snippets

In a broad range of natural language processing tasks, large-scale knowledge-base of paraphrases is anticipated to improve their performance. The key issue in creating such a resource is to establish a practical method of computing semantic equivalence and syntactic substitutability, i.e., paraphrasability, between given pair of expressions. This paper addresses the issues of computing paraphrasability, focusing on syntactic variants of predicate phrases. Our model estimates paraphrasability based on traditional distributional similarity measures, where the Web snippets are used to overcome the data sparseness problem in handling predicate phrases. Several feature sets are evaluated through empirical experiments.