Inductive Logic Programming in Databases: From Datalog to $\mathcal{DL}+log}^{\neg\vee}$

  title={Inductive Logic Programming in Databases: From Datalog to \$\mathcal\{DL\}+log\}^\{\neg\vee\}\$},
  author={Francesca Alessandra Lisi},
  journal={Theory and Practice of Logic Programming},
  pages={331 - 359}
  • F. Lisi
  • Published 12 March 2010
  • Computer Science
  • Theory and Practice of Logic Programming
Abstract In this paper we address an issue that has been brought to the attention of the database community with the advent of the Semantic Web, i.e., the issue of how ontologies (and semantics conveyed by them) can help solving typical database problems, through a better understanding of Knowledge Representation (KR) aspects related to databases. In particular, we investigate this issue from the ILP perspective by considering two database problems, (i) the definition of views and (ii) the… 

Logic-based Rule Learning for the Web of Data

  • F. Lisi
  • Computer Science
  • 2017
This tutorial introduces to Inductive Logic Programming (ILP), being it a major logic-based approach to rule learning, and surveys extensions of ILP that turn out to be suitable for applications to

Learning Onto-Relational Rules with Inductive Logic Programming

This chapter shows how Inductive Logic Programming (ILP), born at the intersection of Machine Learning and Logic Programming and considered as a major approach to Relational Learning, can be adapted to Onto-Relational Learning.

A Formal Characterization of Concept Learning in Description Logics

  • F. Lisi
  • Computer Science
    Description Logics
  • 2012
This paper presents a formal characterization of Concept Learning in DLs which relies on recent results in Knowledge Representation and Machine Learning.

DC Proposal: Ontology Learning from Noisy Linked Data

This doctoral researches will use the approach of Statistical Relational Learning (SRL) to develop learning algorithms for the underlying tasks of ontology learning, and learn OWL axioms inductively from Linked Data under probabilistic setting and analyze the noises in the Linked data on the basis of the learned axiomatic.

A brief guided tour along the borders of Logic Programming with Description Logics

This tutorial talk surveys the literature of the last 20 years concerning the combination of (I)LP and DLs with a particular emphasys on the integration issues to show how many interesting things happen or could happen along the borders of LP with DLs.

Towards Nonmonotonic Relational Learning from Knowledge Graphs

This work makes the first steps towards extending a rule-based approach to KGs in their original relational form, and provides preliminary evaluation results on real-world KGs, which demonstrate the effectiveness of the proposed method.

Technical Report : Exception-enriched Rule Learning from Knowledge Graphs

This work presents a method for effective revision of learned Horn rules by adding exceptions (i.e., negated atoms) into their bodies and demonstrates the effectiveness of the developed method and the improvements in accuracy for KG completion by rule-based fact prediction.

Exception-Enriched Rule Learning from Knowledge Graphs

This work presents a method for effective revision of learned Horn rules by adding exceptions (i.e., negated atoms) into their bodies and demonstrates the effectiveness of the developed method and the improvements in accuracy for KG completion by rule-based fact prediction.

AL-QuIn: An Onto-Relational Learning System for Semantic Web Mining

  • F. Lisi
  • Computer Science
    Int. J. Semantic Web Inf. Syst.
  • 2011
The system -QuIn supports a variant of the frequent pattern discovery task by following the Onto-Relational Learning approach, which takes taxonomic ontologies into account during the discovery process and produces descriptions of a given relational database at multiple granularity levels.

Rule Learning from Knowledge Graphs Guided by Embedding Models

A rule learning method that utilizes probabilistic representations of missing facts is proposed that iteratively extend rules induced from a KG by relying on feedback from a precomputed embedding model over the KG and external information sources including text corpora.



Principles of Inductive Reasoning on the Semantic Web: A Framework for Learning in AL-Log

This paper provides a general framework for learning in ${\mathcal AL}$-log, a hybrid language that integrates the description logic ${\ mathcal ALC}$ and the function-free Horn clausal language Datalog, thus turning out to be a small yet sufficiently expressive subset of SWRL.

Inducing Multi-Level Association Rules from Multiple Relations

This paper presents a novel approach to association rule mining which deals with multiple levels of description granularity and relies on the hybrid language A -log which allows a unified treatment of both the relational and structural features of data.

DL+log: Tight Integration of Description Logics and Disjunctive Datalog

DL +log is defined, a general framework for the integration of Description Logics and disjunctive Datalog rules that allows for a tighter form of integration between DL-KBs and Datalogs rules which overcomes the main representational limits of the approaches based on the safety condition.

Tractable Reasoning and Efficient Query Answering in Description Logics: The DL-Lite Family

It is shown that, for the DLs of the DL-Lite family, the usual DL reasoning tasks are polynomial in the size of the TBox, and query answering is LogSpace in thesize of the ABox, which is the first result ofPolynomial-time data complexity for query answering over DL knowledge bases.

Foundations of Onto-Relational Learning

This paper considers the problem of learning rules from observations that combine relational data and ontologies, and identifies the ingredients of an ILP solution to it, and adopts an instantiation of the KR framework which integrates the DL $\mathcal{SHIQ}$ and positive Datalog.

Bridging the Gap between Horn Clausal Logic and Description Logics in Inductive Learning

A relation of subsumption is defined, called \(\mathcal{B}\)-subsumption, inspired by Buntine’s generalized subsumption, and it is shown that it induces a quasi-order over the space of constrained DATALOG clauses and provides a procedure for checking \(\succeq_{\mathcal_{B}}\) under the object identity bias.

AL-log: Integrating Datalog and Description Logics

A method for query answering in AL-log based on constrained resolution, where the usual deduction procedure defined for Datalog is integrated with a method for reasoning on the structural knowledge.

From Extensional to Intensional Knowledge: Inductive Logic Programming Techniques and Their Application to Deductive Databases

  • Peter A. Flach
  • Computer Science
    Transactions and Change in Logic Databases
  • 1998
This chapter aims at demonstrating that inductive logic programming (ILP), a recently established subfield of machine learning that induces first-order clausal theories from examples, combines very

An ILP Perspective on the Semantic Web

This paper provides a framework for learning Semantic Web rules which adopts Inductive Logic Programming (ILP) as methodological apparatus and AL-log as KR&R setting and inductive hypotheses are represented as constrained Datalog clauses and evaluated against observations by means of coverage relations.

Scaling Up Inductive Logic Programming by Learning from Interpretations

This paper relates the setting to propositional data mining and to the classical ILP setting, and shows that learning from interpretations corresponds to learning from multiple relations and thus extends the expressiveness of propositional learning, while maintaining its efficiency to a large extent.