A New Approach for Automatic Building Field Association Words Using Selective Passage Retrieval

摘要

Large collections of full-text document are now commonly used in automated information retrieval. When the stored document texts are long, the retrieval of complete documents may not be in the users' best interest and extract Filed Association (FA) words is not accurate. In such circumstances, efficient and effective retrieval FA words may be obtained by using passage retrieval strategies designed to retrieve text excerpts of varying size in response to statements of user interest. New approaches are described in this study for implementing selective passage retrieval systems, and identifying text passage response to particular user needs. Moreover an automated system is using for extract accurate FA words from that passage and evaluate the usefulness of the proposed method. From the experimental results, when passage retrieval are accessible leading to the retrieval of additional extracted relevant FA word with corresponding improvements in Recall and Precision. Therefore, Recall and Precision improved by 30% than using whole texts and traditional methods.