You are invited to participate in the upcoming International Workshop on Inductive Reasoning and Machine Learning on the Semantic Web (IRMLeS), to be held as part of the 6th European Semantic Web Conference (ESWC) in June of 2009 in Heraklion, Crete (Greece).

Open, distributed and inherently incomplete nature of the Semantic Web environment posses problems for deductive approaches, traditionally employed to reason with logic-based ontological data. Hence, one may witness a recent trend in the Semantic Web community to propose complementary forms of reasoning, preferably more efficient and noise-tolerant. Promising and already successful approach is the use of inductive and statistical methods as complement to deductive one (for example by adding data mining support to SPARQL query evaluation). It is especially valid when data comes from distributed sources and may be inconsistent.

The IRMLeS workshop puts special attention on the problem of ontology mining and inductive and statistical approximate reasoning. The focus of the workshop is on discussion how machine learning techniques, such as statistical learning methods and inductive forms of reasoning, can work directly on the richly structured Semantic Web data and exploit the Semantic Web technologies, and what is the added value of machine learning methods in the Semantic Web context.

The workshop is meant to be a forum for scientific exchange amongst researchers interested in an interdisciplinary research on the intersection of the Semantic Web with Knowledge Discovery and Machine Learning fields. It is meant to act as a meeting point for the sub-fields from these areas that are interested in research on the challenging problems of such intersection.


Full-day workshop featuring invited talks, presentations (technical, position and application papers) and a wrap-up discussion.


The intended audience for this workshop includes:

  • Semantic Web researchers interested in methods for intelligent data analysis and inductive and statistical approximate reasoning
  • Researchers in machine learning and data mining with interest in the Semantic Web technologies
  • Developers of applications of the Semantic Web technologies that contain components realizing inductive and statistical approximate reasoning, data mining and/or machine learning tasks
  • Knowledge engineers and ontology developers interested in semi-automatic methods for ontology mining, namely ontology construction and evolution


The topics of interest of the workshop include, but are not limited to:

  • Knowledge Discovery and Ontologies
    • Data mining techniques using ontologies
    • Ontology Mining and Knowledge Discovery in ontological knowledge bases
    • Ontology-based interpretation and validation of discovered knowledge
    • Graph mining for ontologies
    • Evaluation methodologies and metrics for the interaction of knowledge discovery and ontologies
  • Inductive Reasoning with Concept Languages
    • inductive concept retrieval and query answering
    • approximate classification
    • inductive methods for ontology construction
    • concept change and novelty detection for ontology evolution
    • rule induction for ontology mapping
    • fuzzy reasoning for ontology construction and evolution
  • Statistical learning in the context of standard Semantic Web languages
    • refinement operators for concept and rule languages
    • concept learning and Web rules learning
    • kernels and instance-based learning for structured representations
    • semantic distances, dissimilarity measures and conceptual clustering
    • extensions of Bayesian methods for concept and rule languages
  • Knowledge-intensive learning from:
    • Linked Open Data and Semantic Networks
    • semi-structured data e.g. semantic mark-up mixed with text content (RSS, RDFa microformats, DublinCore)
  • Applications (life sciences, cultural heritage, semantic multimedia,…) and Tools