University of Leipzig AKSW Homepage | Blog |

Archiv für die Kategorie 'DL-Learner'

AKSW at TU Dresden PLT

June 17, 2011 - 3:34 pm by Jens Lehmann - One comment »

On June 8, I (Jens) visited the process control engineering research group (PLT) of Leon Urbas at the Dresden University of Technology. We first met on the Leipziger Semantic Web Day where Leon Urbas presented interactive Linked Data applications and decided to have a longer meeting later on. I first gave a talk on the Linked Data Lifecycle (slides as PDF), which is a central element of the vision behind the LOD2 project – a cycle of mutual refinement which can help to overcome some of the problems in using Linked Data. It extends on an earlier vision description by Sören and me.

After the initial presentation, we exchanged ideas for collaboration between our groups. The PLT group has a very strong record in large scale practical applications, mobile devices and usability testing. Since their background is automation engineering, they view semantic technologies as a way to connect large networks of knowledge in a flexible manner. They were particularly interested in some of our research and software tools like LIMES, SAIM and OntoWiki. I enjoyed staying at the group and I am looking forward to further meetings.

May 4-5: Leipziger Semantic Web Tag 2011 and Local Media Conferenz

April 16, 2011 - 5:39 pm by Sören Auer - No comments »

Like in the past two years, we again organize a Leipzig Semantic Web Day on May 5th at the marvelous Mediencampus Villa Ida. This year’s theme is “Linked Data  for the Masses”, particularly focusing on its use in enterprises. This event will not only give you the opportunity to discuss current developments around semantic web technologies, but also to get in touch with companies from the German-speaking world. LSWT2011 will have two distinguished keynote speakers: Martin Hepp will share his vision and recent developments around the GoodRelations ecommerce vocabulary with us. The second keynoter Andreas Blumauer from the Semantic Web Company in Vienna will show us how Linked Data can facilitate clean energy.

On the pre-conference day May 4th we will have two tutorials  – an introduction to the Semantic Data Web and another one on the GoodRelations ecommerce vocabulary. Also, on May 4th SoLoMo the Local Media Conference takes place at the Mediencampus, discussing developments around Groupon, Foursquare, Qype, MyHeimat and other local-oriented media.

You can find more information about LSWT at: http://aksw.org/LSWT.

We thank the following LSWT sponsors for their support:




AKSW Conference participation this spring: ESWC, ICWE, WIMS

February 27, 2011 - 1:32 pm by Sören Auer - 2 comments »

Members of AKSW are actively participating in some key (Semantic) Web conferences this spring.

AKSW was already involved in the organization of 8th Extended Semantic Web Conference 2011 with Jens being one of the PC Chairs of the Linked Data track and a number of other AKSW researchers serving as members of the PC of various tracks, workshops and side events. Now also three AKSW submissions were accepted for the main conference programm (having a 23% acceptance rate) at ESWC:

For 11th International Conference on Web Engineering (ICWE 2011), Sören serves as chair of the programme committee and Axel is one of the Demo & Poster Chairs.

Sören is also giving a key-note on “Creating Knowledge Out of Interlinked Data” at the International Conference on Web Intelligence, Mining and Semantics (WIMS’11). WIMS takes place from May 25th-27th in Sogndal, Norway.

DL-Learner Build 2010-08-07 released

August 7, 2010 - 1:32 pm by Jens Lehmann - No comments »

We are happy to announce the next release of DL-Learner, a tool for learning OWL class expressions from examples and background knowledge. It extends Inductive Logic Programming (ILP) to Description Logics and the Semantic Web. The tool has matured over the past 3 years and is meanwhile used in a number of applications. Some features of this release are:

  • support for OWL API 3 and OWL 2
  • ORE (ontology repair and enrichment) tool based on DL-Learner algorithms (soon to be migrated to an own project)
  • several new heuristics, e.g. generalised F-Measure, and efficient stochastic heuristic approximation methods
  • learning algorithms for the EL description logic
  • support for hasValue construct in combination with string datatype
  • support for refining existing definitions (instead of learning from scratch) for CELOE ontology engineering algorithm
  • support for direct Pellet 2 integration and reasoners connected via OWLlink
  • more unit tests, bug fixes and features

DL-Learner can be used to:

  • solve general supervised Machine Learning problems using ontologies as background knowledge (given as OWL files, SPARQL endpoints, etc.), e.g. it was used to predict whether chemicals can cause cancer
  • help knowledge engineers by learning definitions and subclass axioms (see the Protege plugin and OntoWiki plugin)
  • generating user recommendations when browsing knowledge bases

I’d like to thank all contributors, in particular active developers and everyone who sent us valuable feedback.

The tool can be be downloaded here.

ORE 0.2 Released

July 27, 2010 - 11:31 pm by Jens Lehmann - No comments »

Today, we released version 0.2 of the ontology repair and enrichment (ORE) tool. It is a tool for knowledge engineers to improve an OWL ontology through a wizard like repair process and uses state-of-the-art ontology debugging methods. The main feature in version 0.2 is a mode for incrementally detecting inconsistencies in large knowledge bases available as SPARQL endpoints. Using this mode, we have detected inconsistencies and computed justifications in DBpedia Live and OpenCyc. Previously, both knowledge bases were too large to compute justifications on standard hardware to the best of our knowledge, i.e. inconsistencies could not be fixed efficiently. A screencast illustrates this process for the case of DBpedia Live. Thanks to Lorenz Bühmann for his work on ORE.

ORE Homepage | Download | Screencast | AKSW Homepage