Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Structure Discovery in Large Semantic Graphs Using Extant Ontological Scaling and Descriptive Statistics

Conference ·

As semantic datasets grow to be very large and divergent, there is a need to identify and exploit their inherent semantic structure for discovery and optimization. Towards that end, we present here a novel methodology to identify the semantic structures inherent in an arbitrary semantic graph dataset. We first present the concept of an extant ontology as a statistical description of the semantic relations present amongst the typed entities modeled in the graph. This serves as a model of the underlying semantic structure to aid in discovery and visualization. We then describe a method of ontological scaling in which the ontology is employed as a hierarchical scaling filter to infer different resolution levels at which the graph structures are to be viewed or analyzed. We illustrate these methods on three large and publicly available semantic datasets containing more than one billion edges each. Keywords-Semantic Web; Visualization; Ontology; Multi-resolution Data Mining;

Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (US)
Sponsoring Organization:
USDOE
DOE Contract Number:
AC05-76RL01830
OSTI ID:
1092681
Report Number(s):
PNNL-SA-78877; 400470000
Country of Publication:
United States
Language:
English

Similar Records

High Performance Descriptive Semantic Analysis of Semantic Graph Databases
Conference · Thu Jun 02 00:00:00 EDT 2011 · OSTI ID:1030873

Semantic similarity between ontologies at different scales
Journal Article · Fri Apr 01 00:00:00 EDT 2016 · IEEE/CAA Journal of Automatica Sinica · OSTI ID:1337285

High Performance Semantic Factoring of Giga-Scale Semantic Graph Databases
Conference · Mon Oct 04 00:00:00 EDT 2010 · OSTI ID:1222176