A number of specific uses and applications rely on knowledge graphs. Examples include data and information-heavy services such as intelligent content and package reuse, responsive and contextually aware content recommendation, knowledge graph powered drug discovery, semantic search, investment market intelligence, information discovery in regulatory documents, advanced drug safety analytics, etc.

Most often an entity description contains a classification of the entity with respect to a class hierarchy. For instance, when dealing with business information there could be classes Person, Organization and Location. Persons and organizations can have a common superclass Agent. Location usually has numerous sub-classes, e.g., Country, Populated place, City, etc. The notion of class is borrowed by the object-oriented design, where each entity usually belongs to exactly one class.

Graphs Help Text Analysis

It is no surprise that modern text analysis technology makes considerable use of knowledge graphs:

  • Big graphs provide background knowledge, human-like concept and entity awareness, to enable a more accurate interpretation of the text;
  • The results of the analysis are semantic tags (annotations) that link references in the text to specific concepts in the graph. These tags represent structured metadata that enables better search and further analytics;
  • Facts extracted from the text can be added to enrich the knowledge graph, which makes it is much more valuable for analysis, visualization and reporting.

Ontotext Platform implements all flavors of this interplay linking text and big knowledge graphs to enable solutions for content tagging, classification and recommendation. It is a platform for organizing enterprise knowledge into knowledge graphs, which consists of a set of databases, machine learning algorithms, APIs and tools for building various solutions for specific enterprise needs.