Relatedness and TBox-Driven Rule Learning in Large Knowledge Bases

Authors

  • Giuseppe Pirrò Sapienza University of Rome

DOI:

https://doi.org/10.1609/aaai.v34i03.5690

Abstract

We present RARL, an approach to discover rules of the form bodyhead in large knowledge bases (KBs) that typically include a set of terminological facts (TBox) and a set of TBox-compliant assertional facts (ABox). RARL's main intuition is to learn rules by leveraging TBox-information and the semantic relatedness between the predicate(s) in the atoms of the body and the predicate in the head. RARL uses an efficient relatedness-driven TBox traversal algorithm, which given an input rule head, generates the set of most semantically related candidate rule bodies. Then, rule confidence is computed in the ABox based on a set of positive and negative examples. Decoupling candidate generation and rule quality assessment offers greater flexibility than previous work.

Downloads

Published

2020-04-03

How to Cite

Pirrò, G. (2020). Relatedness and TBox-Driven Rule Learning in Large Knowledge Bases. Proceedings of the AAAI Conference on Artificial Intelligence, 34(03), 2975-2982. https://doi.org/10.1609/aaai.v34i03.5690

Issue

Section

AAAI Technical Track: Knowledge Representation and Reasoning