Paraphrase Identification by Text Canonicalization
Yitao Zhang, Jon David Patrick · 2005
This paper proposes an approach to sentencelevel paraphrase identification by text canonicalization. The source sentence pairs are first converted into surface text that approximates canonical forms. A decision tree learning module which employs simple lexical matching features then takes the output canonicalized texts as its input for a supervised learning process. Experiments on the Microsoft Research (MSR) Paraphrase Corpus give comparable performance to other systems that are equipped with more sophisticated lexical semantic and syntactic matching components, with a Confidence-weighted Score of 0.791. An ancillary experiment using the occurrence of nominalizations suggests that the MSR Paraphrase Corpus might not be a rich source for learning paraphrasing patterns. 1