Machine Learning and Ontology Engineering

The MOLE group focuses on combining Semantic Web and supervised Machine Learning technologies. The goal is to improve both quality and quantity of available knowledge by extracting, analysing, enriching and linking existing data. To make obtained results readily available for use in other applications, the group also provides several established open source tools, frameworks and demonstrators.

Research Areas

  • Creating knowledge bases from weakly structured data
  • Quality assurance and enhancement in ontologies
  • Semi-automatic instance matching
  • Supervised Machine Learning in OWL/RDF knowledge bases

Members

Projects

  • aksw.org – a linked data driven web page rendered by OntoWiki site extension
  • AutoSPARQL – Convert a natural language expression to a SPARQL query
  • CSVImport – Representing multi-dimensional statistical data as RDF using the RDF Data Cube Vocabulary
  • DBpedia – Querying Wikipedia like a Semantic Database
  • DBpedia SPARQL Benchmark – a pure RDF benchmark based on actually posed queries
  • DBpediaDQ – Evaluating the quality of DBpedia
  • DeFacto – Deep Fact Validation
  • DEQA – Deep Web Extraction for Question Answering
  • DL-Learner – a tool for supervised Machine Learning in OWL and Description Logics
  • FTS – RDF Version of the Financial Transparency System of the European Commission
  • GeoKnow – Making the Web an Exploratory for Geospatial Knowledge
  • GHO – Publishing and Interlinking the Global Health Observatory Dataset
  • LATC – LOD Around-the-Clock
  • LinkedGeoData – adds a spatial dimension to the Web of Data
  • LOD2 – Creating Knowledge out of Interlinked Data
  • LODStats – a statement-stream-based approach for gathering comprehensive statistics about RDF datasets
  • Navigation-induced Knowledge Engineering by Example – a light-weight methodology for low-cost knowledge engineering by a massive user base
  • NLP Interchange Format (NIF) – an RDF/OWL-based format that allows to combine and chain several NLP tools in a flexible, light-weight way
  • NLP2RDF – Converting NLP tool output to RDF
  • OntoWiki – a tool providing support for agile, distributed knowledge engineering scenarios
  • ORE – A tool for debugging and enriching OWL knowledge bases
  • ReDD-Observatory – Using the Web of Data for Evaluating the Research-Disease Disparity
  • SAIM – (Semi-)Automatic Instance Matcher
  • SemMap – Spatial Semantic Browsing Widgets
  • SPARQL2NL – converting SPARQL queries to natural language
  • SparqlAnalytics – I Know What You Did Last Query
  • Sparqlify – a SPARQL-SQL rewriter
  • TripleCheckMate – Crowdsourcing the evaluation of Linked Data
  • USPatents – Publishing and Interlinking the USPTO Patent Data
  • VeriLinks – verifying links in an arbitrary linkset

Publications

Filters

by (Editors: ) [BibTex of ]

News

SlideWiki at CSEDU2013 Conference ( 2013-05-10T12:21:14+02:00 by Ali Khalili)

2013-05-10T12:21:14+02:00 by Ali Khalili

CSEDU 2013, the International Conference on Computer Supported Education was taking place in Aachen, Germany this year. The conference was addressing different e-learning themes such as Information Technologies Supporting Learning, Learning/Teaching Methodologies and Assessment, Ubiquitous Learning, Social Context and Learning Environments as well as Cloud Education Environments. Read more about "SlideWiki at CSEDU2013 Conference"

Open Data Conference in Seoul ( 2013-05-01T23:25:02+02:00 by Dr. Sören Auer)

2013-05-01T23:25:02+02:00 by Dr. Sören Auer

On the second day of Sören’s short trip to Korea, we participated in the Open Data Conference of the Information Society Agency (NIA). NIA seems to be implementing a comprehensive Open Data strategy (also involving LinkedData). Looks like South Korea is quite advanced in this regard already. Read more about "Open Data Conference in Seoul"

LOD2 STACK USABILITY SURVEY STARTED ( 2013-04-16T13:06:40+02:00 by Sandra Prätor)

2013-04-16T13:06:40+02:00 by Sandra Prätor

In the recent years the LOD2 stack established a collection of applications developed in the context of the LOD2 project, presented as an unified environment. These applications are referred to as components although they can also be installed independently. Read more about "LOD2 STACK USABILITY SURVEY STARTED"

Preview release of RDFaCE special edition for Schema.org ( 2013-04-15T17:12:48+02:00 by Ali Khalili)

2013-04-15T17:12:48+02:00 by Ali Khalili

We are happy to announce the preview release of our RDFaCE WYSIWYM content editor special edition for Schema.org. RDFaCE (RDFa Content Editor) extends the TinyMCE rich text editor to facilitate the authoring of semantic documents. This version of RDFaCE is customized for annotating content in RDFa or Microdata formats based on Schema.org vocabularies. Read more about "Preview release of RDFaCE special edition for Schema.org"

European project BioASQ sets a challenge to push research in biomedical information retrieval and question answering ( 2013-04-12T12:23:14+02:00 by Sandra Prätor)

2013-04-12T12:23:14+02:00 by Sandra Prätor

Every day, approximately 3000 new articles are published in biomedical journals. That averages to more than 2 articles every minute! Managing this large amount of data is a challenge in itself. Read more about "European project BioASQ sets a challenge to push research in biomedical information retrieval and question answering"