Advertisement

Modular, Expandable Typologies

  • Michael K. Bergman
Chapter

Abstract

The idea of a SuperType is exactly equivalent to the root node of a typology, wherein multiple entity types with similar essences and characteristics are related to one another via a natural classification. In this chapter, we discuss the use of types as our general classification structure, and then typologies as modular ways to further organize those types. Further, Peirce was expansive in his recognition of what kinds of objects could be classified, explicitly including ideas, with application to areas such as social classes, human-made objects, sciences, chemical elements, and living organisms. Our typology design has arisen from the intersection of (1) our efforts with SuperTypes to create a computable structure that uses powerful disjoint assertions; (2) an appreciation of the importance of entity types as a focus of knowledge base terminology; and (3) our efforts to segregate entities from other constructs of knowledge bases, including attributes, relations, and annotations. Unlike more interconnected knowledge graphs (which can have many network linkages), typologies are organized strictly along these lines of shared attributes, which both is simpler and provides an orthogonal means for investigating type-class membership. The idea of nested, hierarchical types organized into broad branches of different entity typologies also offers a flexible design for interoperating with a diversity of worldviews and degrees of specificity. The best perspective to see the full listing of the typologies in KBpedia is to inspect the Generals branch of the KKO knowledge graph, which contains about 85 SuperTypes (typologies).

Keywords

Typology Classification 

References

  1. 1.
    A. Marradi, Classification, typology, taxonomy. Qual. Quant. 24(2), 129–157 (1990)CrossRefGoogle Scholar
  2. 2.
    L. Wetzel, Types and tokens, in The Stanford Encyclopedia of Philosophy, ed. by E.N. Zalta (2014)Google Scholar
  3. 3.
    M. Hulswit, Natural classes and causation, in The Online Digital Encyclopedia of, Charles S. Peirce (2000)Google Scholar
  4. 4.
    N. Chinchor, Overview of MUC-7, in MUC-7 Proceedings (1997)Google Scholar
  5. 5.
    A. Brunstein, Annotation Guidelines for Answer Types. Linguistic Data Consortium (2002)Google Scholar
  6. 6.
    S. Sekine, Extended named entity ontology with attribute information, in Proceedings of the Sixth International Language (2008), pp. 52–57Google Scholar
  7. 7.
    X. Ling, D.S. Weld, Fine-grained entity recognition, in Proceedings of the 26th AAAI Conference on Artificial Intelligence (2012)Google Scholar
  8. 8.
    D. Gillick, N. Lazic, K. Ganchev, J. Kirchner, D. Huynh, Context-dependent fine-grained entity type tagging. arXiv:1412.1820 [cs] (2014)Google Scholar
  9. 9.
    S. Murty, P. Verga, L. Vilnis, A. McCallum, Finer grained entity typing with TypeNet. arXiv:1711.05795 [cs] (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Michael K. Bergman
    • 1
  1. 1.Cognonto CorporationCoralvilleUSA

Personalised recommendations