Claudia d'Amato

DL-FOIL Concept Learning in Description Logics

In this paper we focus on learning concept descriptions expressed in Description Logics. After stating the learning problem in this context, a FOIL-like algorithm is presented that can be applied to general DL languages, discussing related theoretical aspects of learning with the inherent incompleteness underlying the semantics of this representation. Subsequently we present an experimental evaluation of the implementation of this algorithm performed on some real ontologies in order to empirically assess its performance.

Mining the Semantic Web

In the Semantic Web vision of the World Wide Web, content will not only be accessible to humans but will also be available in machine interpretable form as ontological knowledge bases. Ontological knowledge bases enable formal querying and reasoning and, consequently, a main research focus has been the investigation of how deductive reasoning can be utilized in ontological representations to enable more advanced applications. However, purely logic methods have not yet proven to be very effective for several reasons: First, there still is the unsolved problem of scalability of reasoning to Web scale. Second, logical reasoning has problems with uncertain information, which is abundant on Semantic Web data due to its distributed and heterogeneous nature. Third, the construction of ontological knowledge bases suitable for advanced reasoning techniques is complex, which ultimately results in a lack of such expressive real-world data sets with large amounts of instance data. From another perspective, the more expressive structured representations open up new opportunities for data mining, knowledge extraction and machine learning techniques. If moving towards the idea that part of the knowledge already lies in the data, inductive methods appear promising, in particular since inductive methods can inherently handle noisy, inconsistent, uncertain and missing data. While there has been broad coverage of inducing concept structures from less structured sources (text, Web pages), like in ontology learning, given the problems mentioned above, we focus on new methods for dealing with Semantic Web knowledge bases, relying on statistical inference on their standard representations. We argue that machine learning research has to offer a wide variety of methods applicable to different expressivity levels of Semantic Web knowledge bases: ranging from weakly expressive but widely available knowledge bases in RDF to highly expressive first-order knowledge bases, this paper surveys statistical approaches to mining the Semantic Web. We specifically cover similarity and distance-based methods, kernel machines, multivariate prediction models, relational graphical models and first-order probabilistic learning approaches and discuss their applicability to Semantic Web representations. Finally we present selected experiments which were conducted on Semantic Web mining tasks for some of the algorithms presented before. This is intended to show the breadth and general potential of this exiting new research and application area for data mining.

A dissimilarity measure for ALC concept descriptions

This work presents a dissimilarity measure for Description Logics that are the theoretical counterpart of the standard representations for ontological knowledge. The focus is on the definition of a dissimilarity measure for ALC concept descriptions, based both on the syntax and on the semantics of the descriptions. An extension of the measure is proposed for involving individuals and then for evaluating their dissimilarity.

Query answering and ontology population: an inductive approach

In order to overcome the limitations of deductive logic-based approaches to deriving operational knowledge from ontologies, especially when data come from distributed sources, inductive (instance-based) methods may be better suited, since they are usually efficient and noise-tolerant. In this paper we propose an inductive method for improving the instance retrieval and enriching the ontology population. By casting retrieval as a classification problem with the goal of assessing the individual class-memberships w.r.t. the query concepts, we propose an extension of the k-Nearest Neighbor algorithm for OWL ontologies based on an entropic distance measure. The procedure can classify the individuals w.r.t. the known concepts but it can also be used to retrieve individuals belonging to query concepts. Experimentally we show that the behavior of the classifier is comparable with the one of a standard reasoner. Moreover we show that new knowledge (not logically derivable) is induced. It can be suggested to the knowledge engineer for validation, during the ontology population task.

On the Influence of Description Logics Ontologies on Conceptual Similarity

Similarity measures play a key role in the Semantic Web perspective. Indeed, most of the ontology related operations such as ontology learning, ontology alignment, ontology ranking and ontology population are grounded on the notion of similarity. In the last few years several similarity functions have been proposed for measuring both concept similarity and ontology similarity. However, they lack of a comprehensive formal characterization that is able to explain their behavior and value added, in particular when the ontologies are formulated in description logics languages like OWL-DL. Concept similarity functions need to be able to deal with the high expressive power of the ontology representation language, and to convey the underlying semantics of the ontology to which concepts refer. We propose a semantic similarity measure for complex Description Logics concept descriptions that elicits the underlying ontology semantics. Furthermore, we theorize a set of criteria that a measure has to satisfy in order to be compliant with a semantic expected behavior.

Tractable Reasoning with Bayesian Description Logics

The DL-Litefamily of tractable description logics lies between the semantic web languages RDFS and OWL Lite. In this paper, we present a probabilistic generalization of the DL-Litedescription logics, which is based on Bayesian networks. As an important feature, the new probabilistic description logics allow for flexibly combining terminological and assertional pieces of probabilistic knowledge. We show that the new probabilistic description logics are rich enough to properly extend both the DL-Litedescription logics as well as Bayesian networks. We also show that satisfiability checking and query processing in the new probabilistic description logics is reducible to satisfiability checking and query processing in the DL-Litefamily. Furthermore, we show that satisfiability checking and answering unions of conjunctive queries in the new logics can be done in LogSpace in the data complexity. For this reason, the new probabilistic description logics are very promising formalisms for data-intensive applications in the Semantic Web involving probabilistic uncertainty.

Statistical Learning for Inductive Query Answering on OWL Ontologies

A novel family of parametric language-independent kernel functions defined for individuals within ontologies is presented. They are easily integrated with efficient statistical learning methods for inducing linear classifiers that offer an alternative way to perform classification w.r.t. deductive reasoning. A method for adapting the parameters of the kernel to the knowledge base through stochastic optimization is also proposed. This enables the exploitation of statistical learning in a variety of tasks where an inductive approach may bridge the gaps of the standard methods due the inherent incompleteness of the knowledge bases. In this work, a system integrating the kernels has been tested in experiments on approximate query answering with real ontologies collected from standard repositories.

Inductive learning for the Semantic Web: What does it buy?

Nowadays, building ontologies is a time consuming task since they are mainly manually built. This makes hard the full realization of the Semantic Web view. In order to overcome this issue, machine learning techniques, and specifically inductive learning methods, could be fruitfully exploited for learning models from existing Web data. In this paper we survey methods for (semi-)automatically building and enriching ontologies from existing sources of information such as Linked Data, tagged data, social networks, ontologies. In this way, a large amount of ontologies could be quickly available and possibly only refined by the knowledge engineers. Furthermore, inductive incremental learning techniques could be adopted to perform reasoning at large scale, for which the deductive approach has showed its limitations. Indeed, incremental methods allow to learn models from samples of data and then to refine/enrich the model when new (samples of) data are available. If on one hand this means to abandon sound and complete reasoning procedures for the advantage of uncertain conclusions, on the other hand this could allow to reason on the entire Web. Besides, the adoption of inductive learning methods could make also possible to dial with the intrinsic uncertainty characterizing the Web, that, for its nature, could have incomplete and/or contradictory information.

The Semantic Web: Trends and Challenges 11th International Conference, ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014, Proceedings

The Semantic Web changes the way we deal with data, because assumptions about the nature of the data that we deal with differ substantially from the ones in established database approaches. Semantic Web data is (i) provided by different people in an ad-hoc manner, (ii) distributed, (iii) semi-structured, (iv) (more or less) typed, (v) supposed to be used serendipitously. In fact, these are highly relevant assumptions and challenges, since they are frequently encountered in all kind of data-centric challenges also in cases where Semantic Web standards are not in use. However, they are only partially accounted for in existing programming approaches for Semantic Web data including (i) semantic search, (ii) graph programming, and (iii) traditional database programming approaches. The main hypothesis of this talk is that we have not yet developed the right kind of programming paradigms to deal with the proper nature of Semantic Web data, because none of the mentioned approaches fully considers its characteristics. Thus, we want to outline empirical investigations of Semantic Web data and recent developments towards Semantic Web programming that target the reduction of the impedance mismatches between data engineering and programming ap-

Conceptual clustering and its application to concept drift and novelty detection

The paper presents a clustering method which can be applied to populated ontologies for discovering interesting groupings of resources therein. The method exploits a simple, yet effective and language-independent, semi-distance measure for individuals, that is based on their underlying semantics along with a number of dimensions corresponding to a set of concept descriptions (discriminating features committee). The clustering algorithm is a partitional method and it is based on the notion of medoids w.r.t. the adopted semi-distance measure. Eventually, it produces a hierarchical organization of groups of individuals. A final experiment demonstrates the validity of the approach using absolute quality indices. We propose two possible exploitations of these clusterings: concept formation and detecting concept drift or novelty.