Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Domain-Specific Knowledge Graph ConstructionAdvanced Topic: Knowledge Graph Completion

Domain-Specific Knowledge Graph Construction: Advanced Topic: Knowledge Graph Completion [With the possible exception of good data collection and ontology design, information extraction and entity resolution are the two most important data-driven steps in a domain-specific knowledge graph construction pipeline. Yet, it is very rarely the case that the story ends there. Once constructed, the knowledge graph is so noisy that additional knowledge graph completion steps often have to be applied to refine the initial KG further. These steps entail procedures like knowledge graph embeddings, which tend to rely on neural techniques, but also graphical models like probabilistic soft logic. After completion, the KG also has to be stored and indexed so that it can be queried in an application framework. The Semantic Web has produced a great deal of research in this realm, along with NoSQL methodologies that have emerged from the mainstream database and knowledge discovery communities. In this chapter, we briefly survey some of these topics. While covering any one of these topics in depth is out of scope, we provide pointers to additional material, in each of these topical areas, for the interested reader.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Domain-Specific Knowledge Graph ConstructionAdvanced Topic: Knowledge Graph Completion

Download PDF
15 pages

Loading next page...
 
/lp/springer-journals/domain-specific-knowledge-graph-construction-advanced-topic-knowledge-ilqhK90PlP
Publisher
Springer International Publishing
Copyright
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2019
ISBN
978-3-030-12374-1
Pages
59 –74
DOI
10.1007/978-3-030-12375-8_4
Publisher site
See Chapter on Publisher Site

Abstract

[With the possible exception of good data collection and ontology design, information extraction and entity resolution are the two most important data-driven steps in a domain-specific knowledge graph construction pipeline. Yet, it is very rarely the case that the story ends there. Once constructed, the knowledge graph is so noisy that additional knowledge graph completion steps often have to be applied to refine the initial KG further. These steps entail procedures like knowledge graph embeddings, which tend to rely on neural techniques, but also graphical models like probabilistic soft logic. After completion, the KG also has to be stored and indexed so that it can be queried in an application framework. The Semantic Web has produced a great deal of research in this realm, along with NoSQL methodologies that have emerged from the mainstream database and knowledge discovery communities. In this chapter, we briefly survey some of these topics. While covering any one of these topics in depth is out of scope, we provide pointers to additional material, in each of these topical areas, for the interested reader.]

Published: Mar 5, 2019

There are no references for this article.