Knowledge Representation and Rule Mining in Entity-Centric Knowledge Bases

Abstract

Entity-centric knowledge bases are large collections of facts about entities of public interest, such as countries, politicians, or movies. They find applications in search engines, chatbots, and semantic data mining systems. In this paper, we first discuss the knowledge representation that has emerged as a pragmatic consensus in the research community of entity-centric knowledge bases. Then, we describe how these knowledge bases can be mined for logical rules. Finally, we discuss how entities can be represented alternatively as vectors in a vector space, by help of neural networks.

Knowledge Graphs

“…In more detail, we call the edges entailed by a rule and the set of positive edges (not including the entailed edge itself) the positive entailments of that rule. The number of entailments that are positive is called the support for the rule, while the ratio of a rule's entailments that are positive is called the confidence for the rule [127]. The goal is to find rules with both high support and confidence.…”

Provenance-Aware Knowledge Representation: A Survey of Data Models and Contextualized Knowledge Graphs

“…17 RDF Schema, an extension of RDF's vocabulary for creating vocabularies, taxonomies, and thesauri; see https://www.w3.org/TR/rdfschema/ for reference. 18 Web Ontology Language (intentionally abbreviated with the W and O swapped as OWL), a fully featured knowledge representation language for the conceptualization of knowledge domains with complex property restrictions and concept relationships; see https://www.w3.org/OWL/ for reference. 19 The last statement captures the provenance of the original statement, namely that the source of the AS number is the Asia-Pacific Network Information Centre (APNIC).…”

“…Approaches to provide alternatives to RDF reification and n-ary relations include -lossless decomposition of RDF graphs: RDF Molecule [42]; -extensions of the RDF data model: N3Logic [43,44], RDF + [45,46], annotated RDF (aRDF) [47], SPO+ Time+Location (SPOTL) [48], RDF* [49], RSP-QL * [50]; -alternate data models: mapping objects to vectors [18], GSMM [51]; -extensions of the RDFS semantics: Annotated RDF Schema [52,53]; -purpose-designed implementation techniques -using annotations: RDF/XML Source Declaration, 25 resource annotation [54]; -via encapsulating provenance information in tuple elements: Provenance Context Entity (PaCE) [55], Singleton property [56]; -using knowledge organization systems; -adding provenance to triples, forming RDF quadruples: N-Quads, 26 Named graphs [57,58], RDF/S graphsets [59], RDF triple coloring [60], nanopublications [61], Hoganification [62]), GraphSource (Sikos et al [40] and Sikos et al [63] collectively); -hybrid approaches, which have multiple traits of the above categories, such as g-RDF [64], which extends RDFS semantics, defines provenance stable models and provenance Herbrand interpretations, and utilizes ontolo- 25 https://www.w3.org/Submission/rdfsource/ 26 https://www.w3.org/TR/n-quads/ gies with positive and strongly negated RDF triples (gRDF triples) and derivation rules.…”

“…This paper is a critical review of alternate approaches to capture provenance for RDF, demonstrates their use in, and provides their quantitative comparison for, the cybersecurity domain (which is known to be reliant on provenance) from various perspectives. Section 2 covers extensions of the standard RDF data model, state-of-the-art annotation frameworks, and purpose-built knowledge organization systems (KOS), including controlled vocabularies 15 and ontologies, 16 typically written in RDFS 17 and OWL, 18 respectively. Section 3 discusses the requirements of RDF triplestores, quadstores, and graph databases to be suitable for storing provenance-aware RDF data, and Sect.…”

“…Note that provenance is a complex term, and its usage varies greatly in different contexts[6] 13. This can be circumvented by using alternate knowledge representations, such as considering entities as embeddings in a vector space, for example[18], however, none of the alternate representations share all the strengths of RDF. 14 https://www.w3.org/TR/rdf11-new/…”