The Semantic Web has ushered in a vast repository of openly available data across various domains, resulting in over ten thousand Knowledge Graphs (KGs) published under the Linked Open Data (LOD) cloud. However, the exploration of these KGs can be time-consuming and resource-intensive, compounded by issues of availability and duplication across distributed and decentralized databases. Addressing these challenges, this thesis investigates methods for improving information retrieval over Linked Data (LD) through conceptual approaches facilitating access via formal and natural language queries. First, RDFSlice is introduced to efficiently select relevant fragments of RDF data from distributed KGs, demonstrating superior performance compared to conventional methods. Second, a novel distributed and decentralized publishing architecture is proposed to simplify data sharing and querying, enhancing reliability and efficiency. Third, a benchmark for evaluating ranking functions for RDF data is created, leading to the development of new ranking functions such as DBtrends and MIXED-RANK. Fourth, a scoring function based on Term Networks is proposed for interpreting factual queries, outperforming traditional information retrieval methods. Lastly, user interface patterns are discussed, and an extension for semantic search is proposed to improve information access in the face of the vast amounts of data available on the LOD cloud. These contributions collectively address key challenges in accessing and utilizing RDF data, offering insights and solutions to facilitate efficient information retrieval and exploration in the Semantic Web era.
| Identifer | oai:union.ndltd.org:DRESDEN/oai:qucosa:de:qucosa:90701 |
| Date | 02 April 2024 |
| Creators | Marx, Edgard Luiz |
| Contributors | Universität Leipzig |
| Source Sets | Hochschulschriftenserver (HSSS) der SLUB Dresden |
| Language | English |
| Detected Language | English |
| Type | info:eu-repo/semantics/acceptedVersion, doc-type:doctoralThesis, info:eu-repo/semantics/doctoralThesis, doc-type:Text |
| Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0029 seconds