The Whyis Knowledge Graph Framework in Action

Merrill Hall October 11, 2018 19:00 - 21:00

Bookmark and Share

Jim McCusker, Sabbir Rashid, Nkechinyere Agu, Kristin Bennett and Deborah McGuinness.  

Abstract:  We will demonstrate a reusable framework for developing knowledge graphs that supports general, open-ended development of knowledge curation, inference, and user interfaces. In recent years knowledge graphs have grown increasingly prominent through commercial and research applications on the Web. Knowledge graphs are becoming more essential to both business and scientific research. Knowledge graphs need to be easily maintainable and usable in sometimes complex application settings. For instance, scaling knowledge graph updates can require developing a knowledge curation pipeline that either replaces the graph wholesale whenever updates are made, or requires detailed tracking of knowledge provenance across multiple data sources. Knowledge graph construction now is not limited only to deductive inference. NLP methods are commonly applied in generating knowledge graphs, and other machine learning methods can be used to produce classifications and predictions that can be expressed as part of a knowledge graph. User interfaces are also key to the success of a knowledge graph, especially when supporting computational users. All of these applications are dependent on high-quality knowledge provenance that is inherent in the design of any knowledge graph system, and not merely an afterthought. Whyis provides a semantic analysis ecosystem: an environment that supports research and development of semantic analytics for which we previously had to build custom applications. Users interact through a suite of knowledge graph views driven by the type of node and view requested in the URL. Knowledge curation methods include Semantic ETL, external linked data mapping, and Natural Language Processing (NLP). Autonomous inference agents expand the available knowledge using traditional deductive reasoning as well as inductive methods that can include predictive models, statistical reasoners, and machine learning.

Keywords:  knowledge graphs;  provenance;  knowledge curation;  nanopublications