Contextual Web search based on semantic relationships

A major challenge faced by keyword-based Web information retrieval systems is how to decipher and interpret users' often highly-ambiguous queries. A number of techniques have been developed in the literature to augment the keyword-based approach to incorporate various types of user and task contexts in the search process. However very few of these studies have examined systematically what constitutes context and how contextual information can be used effectively. In this paper we propose a conceptual framework that classifies various types of context in a Web search environment and present a new semantics-based approach that disambiguates user queries by analyzing the "relationship" context associated with query concepts. Preliminary experimental results indicate that this new approach can help the users find Web information more effectively.