A Critical Review of the Unguided Loose Search (ULS) Process for Natural Language Based Extraction Technique on Relational Databases

Abstract

Formulation of query statements by searchers for submission into relational databases and information retrieval systems have been a serious challenge that often lead to irrelevant search results. This is compounded by the level of uncertainty about the user’s information need and in some cases, unfamiliarity with retrieval system. Evidently, the World Wide Web presents a more established challenge in this area, considering the fact that searchers has little or no training on search techniques on the web. This paper recognizes fuzzy logic system and fuzziness as a tool required to close the gap between automated systems and human thinking.  We realize this stiffness in query presentation as against the flexibility in human thinking and then consider the fuzzy concept as a tool that can be incorporated into a new system to overcome the syntactic problem presented in most relational operations. Thus, the paper proposes a novel approach of natural language query based problems. We propose the use of an Unguided Loose Search (ULS) which involves the use of local appropriator on a fuzzified Natural Language Interface. Our approach incorporates fuzziness in the interface, using the local appropriator, of the database systems rather than within the data itself.  It allows freedom to users since they will not have to learn any specialized syntax such as that of SQL. The result shows that the new querying model called the EFUSQL model is applicable to real life users and can be incorporated into existing databases and query interfaces. The results show that naïve users prefer the new system due to its flexibility and response time