A natural logic system for large knowledge bases

Troels Andreasen, Henrik Bulskov, Jørgen Fischer Nilsson

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

79 Downloads (Pure)


This paper describes principles and structure for a software system that implements a dialect of natural logic for knowledge bases. Natural logics are formal logics that resemble stylized natural language fragments, and whose reasoning rules reflect common-sense reasoning. Natural logics may be seen as forms of extended syllogistic logic. The paper proposes and describes realization of deductive querying functionalities using a previously specified natural logic dialect called NaturaLog. In focus here is the engineering of an inference engine employing as a key feature relational database operations. Thereby the inference steps are subjected to computation in bulk for scaling-up to large knowledge bases. Accordingly, the system eventually is to be realized as a general-purpose database application package with the database being turned logical knowledge base.

Original languageEnglish
Title of host publicationInformation Modelling and Knowledge Bases XXXII
EditorsMarina Tropmann-Frick, Bernhard Thalheim, Hannu Jaakkola, Yasushi Kiyoki, Naofumi Yoshida
PublisherIOS Press BV
Publication date16 Dec 2020
ISBN (Electronic)9781643681405
Publication statusPublished - 16 Dec 2020
Event30th International conference on Information Modeling and Knowledge Bases - Virtual, Online, Germany
Duration: 8 Jun 20209 Jun 2020
Conference number: 30


Conference30th International conference on Information Modeling and Knowledge Bases
CityVirtual, Online
SeriesFrontiers in Artificial Intelligence and Applications

Bibliographical note

Publisher Copyright:
© 2021 The authors and IOS Press.


  • Deductive Querying
  • Large Logical Knowledge Bases
  • Natural Logic
  • Relational Data Base Operations


Dive into the research topics of 'A natural logic system for large knowledge bases'. Together they form a unique fingerprint.

Cite this