Semantic WordNet Based Tree Constructionand Mining on the Progressive Corpus

[摘要] Progressive corpus is handled by storing the intermediate results of the processed data in the database tables (parse tree database) with the help of parse tree. So, that we can get the previous data as well as newly processed data with this we can reduce the reprocessing and minimizes the time. The drawback of such system is when ever user searches of the query it searches based on the tree based search which looks for the exact data and retrieves only the matching content with this we can’t get the semantic data. To overcome this we propose WordNet based tree to handle the incremental corpus which stores the intermediate results in the tables and searches the query based on the phrase based search which retrieves the accurate results and displays the corresponding document names.

[关键词] Text Mining;Query Language;Information Storage and Retrieval;sematic search