Improved TF-IDF weight method based on sentence similarity for spoken dialogue system

This study presents an improved TF-IDF weight method based on sentence similarity for spoken dialogue system to improve the accuracy of retrieval. When the structure database is insufficient to answer user's query, the system then turned to Google Big Data as a response source. The query which structure database cannot handle is processed syntactic analyzed through CKIP Parser. After determined the sentence category, the Head word as a keyword is taken according sentence categories. The reply statement is crawled back from Google Big Data, and output the reply statement through speech synthesis. The experimental result of information retrieval shows that the average accuracy rate of outside test is 84.66%.