Simone Paolo Ponzetto

I joined the Data and Web Science Group in February 2013 as Juniorprofessor and hold since February 2016 the Chair of Information Systems III (Enterprise Data Analysis) as full professor (W3) at the University of Mannheim, where I lead the Natural Language Processing and Information Retrieval group.

jointpapers JOIN-T papers accepted!

A few papers focused around our DFG JOIN-T (Joining Ontologies and semantics INduced from Text) project with the Language Technology Group of the University of Hamburg have been accepted at major conferences in NLP and Semantic Web.

Stefano Faralli, Alexander Panchenko, Chris Biemann and Simone Paolo Ponzetto: The ContrastMedium Algorithm: Taxonomy Induction From Noisy Knowledge Graphs With Just A Few Links. To appear in the proceedings of EACL 2017.

Alexander Panchenko, Eugen Ruppert, Stefano Faralli, Simone Paolo Ponzetto and Chris Biemann: Unsupervised Does Not Mean Uninterpretable: The Case for Word Sense Induction and Disambiguation. To appear in the proceedings of EACL 2017.

Stefano Faralli, Alexander Panchenko, Chris Biemann and Simone Paolo Ponzetto: Linked Disambiguated Distributional Semantic Networks. In proceedings of ISWC 2016.

webisadb WebIsA Database released

We are releasing a very large database of hypernymy relations extracted from the Common Crawl. You can find it here. For details please have a look at the LREC paper describing it (cite it if you find our work useful).

Our WebIsA Database has been used so far as a component in TAXI, our top-performing SemEval TExEval-2 system, as well as for our system participating in the ESWC 016 Open Knowledge Extraction Challenge - for which we received a nomination for best challenge paper!

joint JOIN-T team wins SemEval TExEval-2

A system developed as part of a collaboration between the NLP group of DWS and the Language Technology group of TU Darmstadt has been ranked first in an upcoming SemEval challenge on Taxonomy Extraction Evaluation (TExEval-2).

The results of the challenge can be found here. SemEval is the premier evaluation forum the computational semantics community. This work is part of an ongoing DFG-project (JOIN-T) collaboration between the two groups.

Older news can be found here.