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

Learn More →

A Knowledge Representation PractionaryThe Opportunity

A Knowledge Representation Practionary: The Opportunity [The path to knowledge-based artificial intelligence (KBAI) directly coincides with a framework to aid data interoperability and responsive knowledge management (KM). KBAI, data interoperability, and KM are the three main opportunities covered in this book. A gateway to these opportunities is to address the sources of semantic heterogeneities of information content. A knowledge graph (or ontology) provides the overall schema, and semantic technologies give us a basis to make logical inferences across the knowledge structure and to enable tie-ins to new information sources. We support this graph structure with a platform of search, disambiguation, mapping, and transformation functions, all of which work together to help achieve data interoperability. KBAI is the use of large statistical or knowledge bases to inform feature selection for machine-based learning algorithms. We can apply these same techniques to the infrastructure foundations of KBAI systems in such areas as data integration, mapping to new external structure and information, hypothesis testing, diagnostics and predictions, and myriad other uses to which researchers for decades hoped AI would contribute. We apply natural language processing to these knowledge bases informed by semantic technologies. This approach helps overcome the costs of developing manual training sets in conventional AI by using a class of supervised learning called distant supervision, wherein knowledge bases label entities or other types automatically to then extract features and train a machine learning classifier. Massive public information resources like Wikipedia and Wikidata are common starting points. We may then apply the resulting knowledge supervision to multiple artificial intelligence and KM outcomes.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

A Knowledge Representation PractionaryThe Opportunity

Download PDF
19 pages

Loading next page...
 
/lp/springer-journals/a-knowledge-representation-practionary-the-opportunity-JUxRgpxMh0
Publisher
Springer International Publishing
Copyright
© Springer Nature Switzerland AG 2018
ISBN
978-3-319-98091-1
Pages
65 –84
DOI
10.1007/978-3-319-98092-8_4
Publisher site
See Chapter on Publisher Site

Abstract

[The path to knowledge-based artificial intelligence (KBAI) directly coincides with a framework to aid data interoperability and responsive knowledge management (KM). KBAI, data interoperability, and KM are the three main opportunities covered in this book. A gateway to these opportunities is to address the sources of semantic heterogeneities of information content. A knowledge graph (or ontology) provides the overall schema, and semantic technologies give us a basis to make logical inferences across the knowledge structure and to enable tie-ins to new information sources. We support this graph structure with a platform of search, disambiguation, mapping, and transformation functions, all of which work together to help achieve data interoperability. KBAI is the use of large statistical or knowledge bases to inform feature selection for machine-based learning algorithms. We can apply these same techniques to the infrastructure foundations of KBAI systems in such areas as data integration, mapping to new external structure and information, hypothesis testing, diagnostics and predictions, and myriad other uses to which researchers for decades hoped AI would contribute. We apply natural language processing to these knowledge bases informed by semantic technologies. This approach helps overcome the costs of developing manual training sets in conventional AI by using a class of supervised learning called distant supervision, wherein knowledge bases label entities or other types automatically to then extract features and train a machine learning classifier. Massive public information resources like Wikipedia and Wikidata are common starting points. We may then apply the resulting knowledge supervision to multiple artificial intelligence and KM outcomes.]

Published: Dec 13, 2018

Keywords: Information integration; Data interoperability; Knowledge management; Knowledge-based artificial intelligence

There are no references for this article.