Paraphrasing Predicates from Written Language to Spoken Language Using the Web

There are a lot of differences between expressions used in written language and spoken language. It is one of the reasons why speech synthesis applications are prone to produce unnatural speech. This paper represents a method of paraphrasing unsuitable expressions for spoken language into suitable ones. Those two expressions can be distinguished based on the occurrence probability in written and spoken language corpora which are automatically collected from the Web. Experimental results indicated the effectiveness of our method. The precision of the collected corpora was 94%, and the accuracy of learning paraphrases was 76 %.

• Type: Conference
• Year: 2004
• Where: NAACL
• Authors: Nobuhiro Kaji, Masashi Okamoto, Sadao Kurohashi
• Keywords: NAACL 2004, NAACL 2007, Speech Synthesis Applications, Spoken Language, Written Language