News - NLP and IR

Focus Group: Natural Language Processing and Information Retrieval (Prof. Ponzetto and Prof. Glavaš)

The NLP and IR group at DWS conducts research on integrating knowledge from heterogeneous Web sources – ranging from large raw text collections all the way through collaboratively constructed resources (e.g., Wikipedia) and knowledge bases (DBpedia, Freebase, etc.) – and its application to Natural Language Processing (NLP), Information Analysis and Retrieval tasks. Areas of interest include “deep” NLP techniques for text understanding, ranging from lexical and computational semantics (Word Sense Disambiguation, ontology-based and distributional meaning representations), over information extraction (entities and events), to document understanding and structuring (entity linking, ranking and search, automatic summarization). The group also applies NLP methods to support empirical research in Social Science and Humanities.





 *  joint project with the AI group

**  joint work with the Web-based Information Systems and Services @ HDM Stuttgart


  • SFB 884: Political Economy of Reforms
  • DFG Project JOIN-T: Joining Ontologies and semantics INduced from Text
  • Juniorprofessorenprogramm MWK Baden-Württemberg: Deep semantic models for high-end NLP applications
  • Elite Post-docs program of the the Baden-Württemberg Stiftung: Knowledge consolidation and organization for query-specific Wikipedia construction
  • RiSC Programm MWK Baden-Württemberg: Vision and language understanding beyond literal meaning
  • MWFK BaWü Project: Part-Time Master Program: Data Science
  • Research and Science Center: Trust in Web Reviews
  • Research Data Service Center


Conference Item

  • Alexander Diete, Timo Sztyler, Lydia Weiland and Heiner Stuckenschmidt Improving motion-based activity recognition with ego-centric vision. In: 2018 IEEE International Conference on Pervasive Computing and Communications : PerCom 2018, Athens, Greece, March 19-23, 2018 : PerCom Workshops proceedings; tba. IEEE Computer Society, Piscataway, NJ, 2018.
  • Alexander Panchenko, Dmitry Ustalov, Stefano Faralli, Simone Paolo Ponzetto and Chris Biemann Improving hypernymy extraction with distributional semantic classes. In: LREC 2018, 11th International Conference on Language Resources and Evaluation : 7-12 May 2018, Miyazaki (Japan); tba. European Language Resources Association, ELRA-ELDA, Paris, 2018.


Master and Bachelor Theses

The "ius commune" or "learned laws" (= "roman and canon law” of the Middle Ages) are full of citations which follow a set of generally common rules...


The Web offers a goldmine of information describing a multitude of companies whose products and services can be potentially matched against Web users’...


Recently, there has been much interest to exploit Web-scale resource like the CommonCrawl for intelligent text processing and information extraction...


Recently, we started investigating methods and framework to automatically extract high-quality hypernym relations from Web-scale amounts of data,...


Entity linking, the task of linking mentions of entities in text to wide-coverage concept repositories like DBPedia or Freebase, has so far...