Keyword Search on Probabilistic XML Data Based on ELM

Abstract

This paper describe a keyword search measure on probabilistic XML data based on ELM (Extreme Learning Machine). We use this method to carry out keyword search on probabilistic XML data. A probabilistic XML document differs from a traditional XML document to realize keyword search in the consideration of possible world semantics. A probabilistic XML data can be seen as a set of nodes consisting of ordinary nodes and distributional nodes. ELM has good performance in text classification applications. As the typical semi-structured data, the label of XML data possesses the function of definition self. Label and keyword which has been contained in the node can be seen as the text data of the node. ELM offers significant advantages such as fast learning speed, ease of implementation and classification nodes effectively. Keyword search on the set after it classified by using ELM can pick up the speed of query. This paper uses ELM to classify nodes and carry keyword search on the set which has been classified. The experiments can show that the speed of query can receive significant improvement.