Semantic form-based guided search system

摘要

Semantic Search importance is becoming more valuable each day as the extent of information on the web increases, thus making information mining a tedious operation. In the past few years various solutions appeared to support in the propagation of semantic search like natural language interfaces (NLIs) and guided systems, but unfortunately these haven't reached maturity yet and still have their set of drawbacks. Natural language interfaces have low precision rates and guided systems perform query validation only at a syntactical level. In this paper we are looking for the best of both worlds where we adopt not only the simplicity of natural language interfaces but also the precision of guided systems. However our system has a new twist were it adds the form-based interface to the mechanism of the guided-based semantic search engines to produce more accurate results. Within our research we constructed a comparison between a NLI and our system as a proof of our approach. So we proposed a Semantic Form-Based Guided Search System (SFBGSS), which combines the advantages of both the NLIs and the guided-based semantic search engines. The figures of the precision and recall for the proposed SFBGSS were 98% and 93% respectively. These results outperformed the precision and recall of NLP-Reduce [16] by 38% and 43% respectively.