Structured machine learning: the next ten years

@article{Dietterich2008StructuredML,
  title={Structured machine learning: the next ten years},
  author={Thomas G. Dietterich and Pedro M. Domingos and Lise Getoor and Stephen Muggleton and Prasad Tadepalli},
  journal={Machine Learning},
  year={2008},
  volume={73},
  pages={3-23}
}
The field of inductive logic programming (ILP) has made steady progress, since the first ILP workshop in 1991, based on a balance of developments in theory, implementations and applications. More recently there has been an increased emphasis on Probabilistic ILP and the related fields of Statistical Relational Learning (SRL) and Structured Prediction. The goal of the current paper is to consider these emerging trends and chart out the strategic directions and open problems for the broader area… 
Inductive logic programming at 30: a new introduction
TLDR
As ILP turns 30, a new introduction to the field is provided, introducing the necessary logical notation and the main learning settings; the building blocks of an ILP system are described; several systems on several dimensions are compared; and key application areas are highlighted.
ILP turns 20
TLDR
Using the analogy of a human biography, this paper recalls the development of the subject from its infancy through childhood and teenage years and shows how in each phase ILP has been characterised by an attempt to extend theory and implementations in tandem with theDevelopment of novel and challenging real-world applications.
Biography and future challenges
TLDR
Using the analogy of a human biography this paper re- calls the development of the subject from its infancy through childhood and teenage years, and shows how in each phase ILP has been characterised by an attempt to extend theory and implementations in tandem with theDevelopment of novel and challenging real-world applications.
Decision-Theoretic Logic Programs
TLDR
A new framework, Decision-theoretic Logic Programs (DTLPs), is proposed that extends Probabilistic ILP models by integrating desicion-making features developed in Statistical Decision Theory area and an implementation of DTLPs using Stochastic Logic Programs is introduced.
Towards the definition of learning systems with configurable operators and heuristics ?
TLDR
A general rule-based learning setting where operators can be defined and customised for each kind of problem, and an adaptive and flexible rethinking of heuristics, with a model-based reinforcement learning approach, to tame the search space.
ILP turns 20 - Biography and future challenges
TLDR
The development of the subject from its infancy through childhood and teenage years is recalled using the analogy of a human biography to show how in each phase ILP has been characterised by an attempt to extend theory and implementations in tandem with the development of novel and challenging real-world applications.
Research on Markov Logic Networks
TLDR
This paper addresses the theoretical model of Markov logic networks (MLNs), weight and structure learning of MLNs comprehensively, and finally presents future works ofMLNs.
CarpeDiem: Optimizing the Viterbi Algorithm and Applications to Supervised Sequential Learning
TLDR
CarpeDiem is proposed, a novel algorithm allowing the evaluation of the best possible sequence of labels with a sub-quadratic time complexity that is never asymptotically worse than the Viterbi algorithm, thus confirming it as a sound replacement.
Statistical Learning for Relational and Structured Data
TLDR
A semi-generative approach to parameter learning for stochastic grammars is proposed, showing applications to natural language parsing and RNA secondary structure prediction, and an extension of standard MLNs is presented, in order to handle continuous features and to embed discriminative classifiers within that framework.
10 Years of Probabilistic Querying - What Next?
TLDR
This work believes that natural-language processing and information extraction will remain a driving factor and in fact a longstanding challenge for developing expressive representation models which can be combined with structured probabilistic inference--also for the next decades to come.
...
...

References

SHOWING 1-10 OF 122 REFERENCES
Mathematical applications of inductive logic programming
TLDR
It is argued that mathematics is not only a challenging domain for the application of ILP systems, but that mathematics could be a good domain in which to develop a new generation of systems which integrate various reasoning techniques.
Learning the structure of Markov logic networks
TLDR
An algorithm for learning the structure of MLNs from relational databases is developed, combining ideas from inductive logic programming (ILP) and feature induction in Markov networks.
Inductive logic programming - techniques and applications
TLDR
Applications of inductive logic programming: learning rules for early diagnosis of rheumatic diseases finite element mesh design an overview of selected ILP applications.
Advances in Inductive Logic Programming
TLDR
A state-of-the-art overview of Inductive Logic Programming is provided, based on the succesful ESPRIT basic research project no. 6020, which can be used as a thorough introduction to the field.
Probabilistic Inductive Logic Programming
TLDR
This chapter outlines three classical settings for inductive logic programming, namely learning from entailment, learning from interpretations, and learning from proofs or traces, and shows how they can be adapted to cover state-of-the-art statistical relational learning approaches.
Mapping and Revising Markov Logic Networks for Transfer Learning
TLDR
This paper considers transfer learning with Markov logic networks (MLNs), a powerful formalism for learning in relational domains and presents a complete MLN transfer system that first autonomously maps the predicates in the source MLN to the target domain and then revises the mapped structure to further improve its accuracy.
Explanation-based learning: An alternative view
TLDR
Six specific problems with the previously proposed framework for the explanation-based approach to machine learning are outlined and an alternative generalization method to perform explanation- based learning of new concepts is presented.
Learning an Approximation to Inductive Logic Programming Clause Evaluation
TLDR
This work outlines three techniques that make use of the trained evaluation-function approximator in order to reduce the computation required during an ILP hypothesis search, and shows that the clause evaluation function can be accurately approximated.
Probabilistic First-Order Theory Revision from Examples
TLDR
The results of a theory modified only in places that are responsible for the misclassification of some examples are compared with the one that was modified in the entire structure using three databases and considering four probabilistic score functions, including conditional log likelihood.
Statistical predicate invention
TLDR
This work proposes an initial model for SPI based on second-order Markov logic, in which predicates as well as arguments can be variables, and the domain of discourse is not fully known in advance.
...
...