Knowledge Integration and Language Technologies

What kind of smart applications can we build, if we were able to integrate all available knowledge, data and language resources in a meaningful way? While Turing's imitation game is exciting, we are focussing on the actual knowledge engineering to build information machines that enable humans to perform more efficiently in their tasks. To achieve this goal, we believe the following two prerequisites must be met:

  1. Knowledge and Data must be rendered discoverable and then transformed, linked, enriched and integrated homogeneously in a huge semantic knowledge graph (DBpedia)
  2. Language Technologies must be on the one hand leveraged to understand, categorize and structure available textual content in all its forms. On the other hand, language technology must assist in building adequate interfaces that allow humans to interact effectively with data and information via discovery, querying and reorganization.

Research in this group focusses on contextualising data and ontologies as well as capturing deep linguistic knowledge to improve machine understanding. Besides research, we are taking the extra effort to undertake transfer and innovation projects and support industrial applications such as in the JURION use case.

Main contact: Dr.-Ing. Sebastian Hellmann

Projects

  • 5. Leipziger Semantic Web Tag (LSWT2013)Von Big Data zu Smart Data
  • ALIGNEDAligned, Quality-centric Software and Data Engineering
  • DBpediaQuerying Wikipedia like a Semantic Database
  • DBpediaDQUser-driven quality evaluation of DBpedia
  • DBpediaDQCrowdCrowdsourcing DBpedia Quality Assessment
  • DL-Learnera tool for supervised Machine Learning in OWL and Description Logics
  • Dockerizing Linked DataKnowledge Base Shipping to the Linked Open Data Cloud
  • FREMEOpen Framework of E-services for Multilingual and Semantic Enrichment of Digital Content
  • LIDERLinked Data as an enabler of cross-media and multilingual content analytics for enterprises across Europe
  • LOD2Creating Knowledge out of Interlinked Data
  • MEX VocabularyA Light-Weight Interchange Format for Machine Learning Experiments
  • MMoOnThe Multilingual Morpheme Ontology and Language Inventories
  • Navigation-induced Knowledge Engineering by Examplea light-weight methodology for low-cost knowledge engineering by a massive user base
  • NIF4OGGDNatural Language Interchange Format for Open German Governmental Data
  • NLP Interchange Format (NIF)an RDF/OWL-based format that allows to combine and chain several NLP tools in a flexible, light-weight way
  • NLP2RDFConverting NLP tool output to RDF
  • RDFUnitan RDF Unit-Testing suite
  • Smart Data WebCreation of an industry knowledge base for the German industry.
  • TripleCheckMateCrowdsourcing the evaluation of Linked Data

Publications

Filters

by (Editors: ) [BibTex of ]

News

AKSW Colloquium, 18.07.2016, AEGLE and node2vec ( 2016-07-18T14:56:44+02:00 TommasoSoru)

2016-07-18T14:56:44+02:00 TommasoSoru

On Monday 18.07.2016, Kleanthi Georgala will give her Colloquium presentation for her paper “An Efficient Approach for the Generation of Allen Relations”, that was accepted at the European Conference on Artificial Intelligence (ECAI) 2016. Read more about "AKSW Colloquium, 18.07.2016, AEGLE and node2vec"

AKSW Colloquium, 04.07.2016. Big Data, Code Quality. ( 2016-06-29T12:34:35+02:00 by Ivan Ermilov)

2016-06-29T12:34:35+02:00 by Ivan Ermilov

On the upcoming Monday (04.07.2016), AKSW group will discuss topics related to Semantic Web and Big Data as well as programming languages and code quality. Read more about "AKSW Colloquium, 04.07.2016. Big Data, Code Quality."

Accepted Papers of AKSW Members @ Semantics 2016 ( 2016-06-27T12:50:01+02:00 by Sandra Bartsch)

2016-06-27T12:50:01+02:00 by Sandra Bartsch

This year’s SEMANTiCS conference which is taking place between September 12 – 15, 2016 in Leipzig recently invited for the submission of research papers on semantic technologies. Read more about "Accepted Papers of AKSW Members @ Semantics 2016"

AKSW Colloquium, 27.06.2016, When owl:sameAs isn’t the Same + Towards Versioning for Arbitrary RDF Data ( 2016-06-26T15:46:24+02:00 by Marvin Frommhold)

2016-06-26T15:46:24+02:00 by Marvin Frommhold

In the next Colloquium, June the 27th at 3 PM, two papers will be presented: When owl:sameAs isn’t the Same: An Analysis of Identity in Linked Data André Valdestilhas will present the paper “When owl:sameAs isn’t the Same: An Analysis of Identity … Continue reading → Read more about "AKSW Colloquium, 27.06.2016, When owl:sameAs isn’t the Same + Towards Versioning for Arbitrary RDF Data"

Should I publish my dataset under an open license? ( 2016-06-22T11:41:28+02:00 by Dr.-Ing. Sebastian Hellmann)

2016-06-22T11:41:28+02:00 by Dr.-Ing. Sebastian Hellmann

Undecided, stand back we know flowcharts:   Taken from my slides for my keynote  at TKE: Linguistic Linked Open Data, Challenges, Approaches, Future Work from Sebastian Hellmann Read more about "Should I publish my dataset under an open license?"