Inductive Logic Programming

Word sense disambiguation (WSD) is the problem of determining the sense of a multi-sense word in a given context. It is one of the important processes needed for natural language processing applications. Inductive Logic Programming (ILP) is the area of artificial intelligence which contains machine learning and logic programming. It aims to build first- order theories from examples and background knowledge, which are also represented by first- order clauses. The richness of first order logic employed in ILP can hopefully provide advantages for NLP applications such as WSD. In this study, a corpus-based WSD application is improved by using ILP.

The spreadsheet application is among the most widely used computing tools in the modern society. It provides great usability and usefulness, and it easily enables a non-programmer to perform programming-like tasks in a visual tabular " pen and paper " approach. However, due to its mono-directional dataflow, spreadsheets are mostly limited to bookkeeping-like applications. This paper shows how the spreadsheet computing paradigm is extended to break through this limitation for solving constraint satisfaction problems. We present an enhanced spreadsheet system where finite-domain constraint solving is well supported in a visual environment. A spreadsheet-specific constraint language is constructed for general users to specify constraints among data cells in a declarative and scalable way. The new spreadsheet system significantly simplifies the development of many constraint-based applications using a visual tabular interface. Examples are given to illustrate the usability and usefulness of the extended spreadsheet paradigm.

Motivated by the goal of being able to manipulate complex objects symbolically, we propose a method of integrating functional, logic and object-oriented programming paradigms. Our method assumes the existence of an object-expression evaluator (i.e. the underlying Smalltalk interpreter) and relies on transformations and calls to this object-expression evaluator as its means of computation. Programs of the combined paradigm consist of conditional rewrite rules augmented to incorporate object expressions. 1

Word sense disambiguation (WSD) is the problem of determining the sense of a multi-sense word in a given context. It is one of the important processes needed for natural language processing applications. Inductive Logic Programming (ILP) is the area of artificial intelligence which contains machine learning and logic programming. It aims to build first- order theories from examples and background knowledge, which are also represented by first- order clauses. The richness of first order logic employed in ILP can hopefully provide advantages for NLP applications such as WSD. In this study, a corpus-based WSD application is improved by using ILP.

The Variable Precision Rough Set Inductive Logic Programming model (VPRSILP model) extends the Variable Precision Rough Set (VPRS) model to Inductive Logic Programming (ILP). The generic Rough Set Inductive Logic Programming (gRS-ILP) model provides a framework for ILP ...

Meta-interpretive learning (MIL) is a form of inductive logic programming that learns logic programs from background knowledge and examples. We claim that adding types to MIL can improve learning performance. We show that type checking can reduce the MIL hypothesis space by a cubic factor. We introduce two typed MIL systems: Metagol_T and HEXMIL_T, implemented in Prolog and Answer Set Programming (ASP), respectively. Both systems support polymorphic types and can infer the types of invented predicates. Our experimental results show that types can substantially reduce learning times.

ILP systems induce first-order clausal theories performing a search through very large hypotheses spaces containing redundant hypotheses. The generation of redundant hypotheses may prevent the systems from finding good models and increases the time to induce them. In this paper we propose a classification of hypotheses redundancy and show how expert knowledge can be provided to an ILP system to avoid it. Experimental results show that the number of hypotheses generated and execution time are reduced when ...

This paper presents a supervised machine learning approach to incrementally learn and segment affixes using generic background knowledge.  We used Prolog script to split affixes from the Amharic word for further morphological analysis. Amharic, a Semitic language, has very complex inflectional and derivational verb morphology, with many possible prefixes and suffixes which are used to show various grammatical features. Further segmentation of the affixes into valid morphemes is a challenge addressed in this paper. The paper demonstrates how incremental and easy-to-complex examples can be used to learn such language constructs. The experiment revealed that affixes could be further segmented into valid prefixes and suffixes using a generic and robust string manipulation script by the help of an intelligent teacher who presents examples in incremental order of complexity allowing the system to gradually build its knowledge. The system is able to do the segmentation with 0.94 Precision and 0.97 Recall rates.

Abstract. Acquiring and maintaining Semantic Web rules is very demanding and can be automated though partially by applying Machine Learning algorithms. In this paper we show that the form of Machine Learning known under the name of Inductive Logic Programming ...

This chapter starts with a general introduction to protein folding. We then present a probabilistic method of dealing with multi-class classification, in particular multi-class protein fold prediction, using Stochastic Logic Programs (SLPs). Multi-class prediction attempts to classify an observed datum or example into its proper classification given that it has been tested to have multiple predictions. We apply an SLP parameter estimation algorithm to a previous study in the protein fold prediction area, in which logic programs have been learned by Inductive Logic Programming (ILP) and a large number of multiple predictions have been detected. On the basis of several experiments, we demonstrate that PILP approaches (eg. SLPs) have advantages for solving multi-class (protein fold) prediction problems with the help of learned probabilities. In addition, we show that SLPs outperform ILP plus majority class predictor in both predictive accuracy and result interpretability.

Discovering knowledge from chemical compound structure data is a challenge task in KDD. It aims to generate hypotheses describing activities or characteristics of chemical compounds from their own structures. Since each compound composes of several parts with complicated relations among them, traditional mining algorithms cannot handle this kind of data efficiently. In this research, we apply Inductive Logic Programming (ILP) for classifying chemical compounds. ILP provides comprehensibility to learning results and capability to handle more complex data consisting of their relations. Nevertheless, the bottleneck for learning first-order theory is enormous hypothesis search space which causes inefficient performance by the existing learning approaches compared to the propositional approaches. We introduces an improved ILP approach capable of handling more efficiently a kind of data called multiple-part data, i.e., one instance of data consists of several parts as well as relations among parts. The approach tries to find hypothesis describing class of each training example by using both individual and relational characteristics of its part which is similar to finding common substructures among the complex relational instances. Chemical compound data is multiple-part data. Each compound is composed of atoms as parts, and various kinds of bond as relations among atoms. We then apply the proposed algorithm for chemical compound structure by conducting experiments on two real-world datasets: mutagenicity in nitroaromatic compounds and dopamine antagonist compounds. The experiment results were compared to the previous approaches in order to show the performance of proposed approach.

Meta-interpretive learning (MIL) is a form of inductive logic programming. MIL uses second-order Horn clauses, called metarules, as a form of declarative bias. Metarules define the structures of learnable programs and thus the hypothesis space. Deciding which metarules to use is a trade-off between efficiency and expressivity. The hypothesis space increases given more metarules, so we wish to use fewer metarules, but if we use too few metarules then we lose expressivity. A recent paper used Progol's entailment reduction algorithm to identify irreducible, or minimal, sets of metarules. In some cases, as few as two metarules were shown to be sufficient to entail all hypotheses in an infinite language. Moreover, it was shown that compared to non-minimal sets, learning with minimal sets of metarules improves predictive accuracies and lowers learning times. In this paper, we show that entailment reduction can be too strong and can remove metarules necessary to make a hypothesis more specific. We describe a new reduction technique based on derivations. Specifically, we introduce the derivation reduction problem, the problem of finding a finite subset of a Horn theory from which the whole theory can be derived using SLD-resolution. We describe a derivation reduction algorithm which we use to reduce sets of metarules. We also theoretically study whether certain sets of metarules can be derivationally reduced to minimal finite subsets. Our experiments compare learning with entailment and derivation reduced sets of metarules. In general, using derivation reduced sets of metarules outperforms using entailment reduced sets of metarules, both in terms of predictive accuracies and learning times.

This paper gives a survey of (symbolic) machine learning methods, that exhibit significant features of adaptivity. The paper discusses incremental learning, learning in dynamically changing domains, knowledge integration, theory revision, case based reasoning and inductive logic programming.

One promising family of search strategies to alleviate runtime and storage requirements of ILP systems is that of stochastic local search methods, which have been successfully applied to hard propositional tasks such as satisfiability. Stochastic local search algorithms for propositional satisfiability benefit from the ability to quickly test whether a truth assignment satisfies a formula. Because of that many possible solutions can be tested and scored in a short time. In contrast, testing whether a clause covers an example in ILP takes much longer, so that far fewer possible solutions can be tested in the same time. Therefore in this paper we investigate stochastic local search in ILP using a relational propositionalized problem instead of directly use the first-order clauses space of solutions.

The concept of logic databases can serve as a clear and expressive foundation of various kinds of information systems. However, classical logic languages refer to a single database state, whereas in modern information systems it is necessary to take dynamic behaviour into account. For this purpose, several update languages have been proposed, among them [1,5,6,9,16,17,18,23], which allow to specify complex transitions from one database state to another. From the evaluation point of view, a complex state transition can and should be considered as a transaction. Up to now, the isolation property of transactions has been poorly addressed in the context of logic update languages, although it is an important problem even for classical, sequential transactions (see

Numerous measures are used for performance evaluation in machine learning. In predictive knowledge discovery, the most frequently used measure is classification accuracy. With new tasks being addressed in knowledge discovery, new measures appear. In descriptive knowledge discovery, where induced rules are not primarily intended for classification, new measures used are novelty in clausal and subgroup discovery, and support and confidence in association rule learning. Additional measures are needed as many descriptive knowledge discovery tasks involve the induction of a large set of redundant rules and the problem is the ranking and filtering of the induced rule set. In this paper we develop a unifying view on some of the existing measures for predictive and descriptive induction. We provide a common terminology and notation by means of contingency tables. We demonstrate how to trade off these measures, by using what we call weighted relative accuracy. The paper furthermore demonstrates that many rule evaluation measures developed for predictive knowledge discovery can be adapted to descriptive knowledge discovery tasks.