:: Home | Deutsch | Print ::

Natural Language Processing

Technical devices are getting more versatile and sophisticated all the time. To make their use more intuitive, the NLP group develops software facilitating the multimodal dialogue between users and machines, applying both statistical and symbolic methods. The group's research focus lies on the semantics and pragmatics of discourse.



ANNOUNCEMENTS

We have available two PhD positions, one of them will be part of our latest project:
CoSyne: A project on Multi-lingual Content Synchronization with Wikis -- an ICT-STREP project funded by the European Commision. The project will start in March 2010. More news later!

We are building WikiNet -- a multi-lingual large scale ontology based on Wikipedia. Currently it contains approximately 3 million concepts and 20+ million relations extracted from the 20090703 version of Wikipedia.

We have papers on many exciting topics this year!
Katja published a paper on summarization at EACL -- Company Oriented Extractive Summarization of Financial News -- , and one on text generation at NAACL -- Tree Linearization in English: Improving Language Model Based Approaches.
Viola Ganter has a short paper on sentiment analysis at ACL --
Finding hedges by chasing weasels: Hedge detection using Wikipedia tags and shallow linguistic features.
Stephanie Schuldes' paper at UCNLG is about
Creating an annotated corpus for generating walking directions.
Vivi has papers on metonymy resolution (Combining collocations, lexical and encyclopedic knowledge for metonymy resolution) and grammatical gender (What's in a name? In some languages, grammatical gender) at EMNLP.



Two new projects in the NLP group:

1. A project on semantic-driven synchronous generation of language and 3D scenes funded in the framework of the Innovation Fonds for Frontier Research of the Excellence Initiative at the University of Heidelberg. We work together with the Computational Linguistics Department and the Interdisciplinary Center for Scientific Computing at the University of Heidelberg. -- Interested in a PhD position in this project? See here!

2. JUMAS -- Judicial Management by Digital Libraries Semantics. An IST-STREP project funded by the European Commision.

We are releasing a taxonomy automatically generated from the network of categories in Wikipedia (RDF Schema format).


Less new news here.

 

Projects
 
Materials


Old Projects:
 
   
   
page last modified: 19.11.2009,10:10


Group Leader

Group Leader, Dr. Michael Strube
Phone: +49 (0)6221 - 533 - 243
Fax: +49 (0)6221 - 533 - 298
more >>




Research Staff
Viola Ganter
Phone: +49 (0)6221 - 533 - 238
Fax: +49 (0)6221 - 533 - 298
more >>



Dr. Vivi Nastase
Phone: +49 (0)6221 - 533 - 253
Fax: +49 (0)6221 - 533 - 298
more >>




Scholarship Holders
Jie Cai
Phone: +49 (0)6221 - 533 - 238
Fax: +49 (0)6221 - 533 - 298




Bo Li
Phone: +49 (0)6221 - 533 - 253
Fax: +49 (0)6221 - 533 - 298





Students
Sarah Ebling
Fax: +49 (0)6221 - 533 - 298




Elzbieta Kulig
Phone: +49 (0)6221 - 533 - 228
Fax: +49 (0)6221 - 533 - 298




Éva Mújdricza-Maydt
Phone: +49 (0)6221 - 533 - 228
Fax: +49 (0)6221 - 533 - 298




Helge Rüdiger Wolf
Phone: +49 (0)6221 - 533 - 228
Fax: +49 (0)6221 - 533 - 298




Caecilia Zirn
Phone: +49 (0)6221 - 533 - 228
Fax: +49 (0)6221 - 533 - 298





Interns
Alexander Judea
Fax: +49 (0)6221 - 533 - 298





Guest Scientists
Stephanie Schuldes
Phone: +49 (0)6221 - 533 - 253
Fax: +49 (0)6221 - 533 - 298




© EML Research gGmbH