A Ranking-Based Document Retrieval Model: The TEXPROS Approach

Abstract

In this paper, a ranking-based document retrieval model is proposed to incorporate with the browsing process. In TEXPROS (TEXt PROcessing System), the interactive browsing process is designed to allow the interactions between the system and a user for forming a strategy of retrieving documents and information from the document base. By gathering information, users could reformulate queries dynamically. During the browsing sessions, a predicate augmented an infrastructure (called Operation Network) is used to present the information about the document types, the synopses of the documents and where documents are deposited. The outcome of using the concept-based retrieval for searching requested documents with partial descriptions could be a large volume of returned documents. The ranking model is used to rank the returned documents according to the degree of their relevancy to the query. Based on the TEXPROS's dual models, an approach to creating the representatives of documents and queries is described as a basis for the proposed ranking model. By integrating the ranking model and the browsing system as a whole, an open retrieval environment is created, which can be customized for different application domains.