Ontology-Based Natural Query Retrieval Using Conceptual Graphs

As compared to the classical library model of printed materials, digital library offers a more efficient way to browse and search for scholarly information in a networked environment. Currently, the most common way of searching and retrieving information from digital libraries is still by means of keyword-based queries. Over the past many years, there have been many attempts to enhance the query formalism to allow users to retrieve information in a more effective manner. Among them, natural query that is expressed using natural language is obviously the most natural form of search requests. However, typical NLP techniques for natural query retrieval suffer from high cost of complexity. In addition, they are also not very effective when dealing with grammatically imprecise search requests. In this paper, we propose a novel ontology-based approach for natural query retrieval of scholarly information using conceptual graphs. The paper will present the proposed ontology-based approach and its experimental results. The proposed approach has achieved some promising initial results.