الفهرس 
CHAPTER 1: Introduction and OverviewOnly 14 pages are availabe for public view
 |  | from | 93 |  |  |
| | | from | 93 | | |
Abstract
This thesis discusses the idea of how a user submits a text-based query without knowing the schema of the underlying knowledge base and then converts this text into a formal query that deals with the Resource Description Framework (RDF) knowledge base. However, the user doesn’t know anything about the structure and syntax of this formal query. Semantic Protocol And Resource description framework Query Language (SPARQL ), which is a powerful method for querying the large and increasing number of linked open data repositories available through the Semantic Web.
A single query to a search engine on the internet produces thousands of so-called ”matched documents,” some related and others not. Users typically suffer from organizing and understanding such massive amounts of information, much of which is likely to be irrelevant. Because structural information and meta-data (like RDF) are available to support context-based and category-based searches. So when a user submits a query like ”Who is the writer of the Semantic Web book?” utilizing Semantic Web technologies, these systems will return a person’s name as the answer, which cannot be found using Google or any other search engine’s ”words based search.” Since a considerable amount of the information retrieved is likely unrelated, sophisticated information retrieval systems based on Semantic Web technologies, such as RDF and Web Ontology Language (OWL), can help end users organize vast amounts of data to address this issue.
The main focus is the conversion of user keywords into a formal query. Without understanding the dataset’s underlying structure, how can a user input a text-based query and then convert this text into SPARQL language that deals with the RDF knowledge base? The user may not know the structure and syntax of SPARQL, a formal query language and a sophisticated tool for the Semantic Web’s vast and growing collection of interconnected open data repositories.
Translating user inquiries into SPARQL queries is not a simple or quick process. It is a complex question that belongs to the question-answering (QA) category. Building a QA system should be done in three steps: question analysis, document (database) analysis, and answer extraction. These three also each comprise several tasks. For instance, question analysis includes feature selection and extraction, classifier construction, and evaluation to determine the Expected Answer Type (EAT). However, if your query format is unchanging, you can ask users to submit their questions in that format, making it simpler to match user inquiries to SPARQL queries and obtain the results. As such, the primary purpose of this study is to discuss different methods that convert natural language into SPARQL query, how each operates, and the output.