Focus Group: Natural Language Processing and Information Retrieval
(Prof. Ponzetto)
The NLP and IR group at DWS conducts research on methods for knowledge acquisition and natural language processing (NLP), as well as their application to support empirical research in (Computational) Social Sciences and (Digital) Humanities. In our work, we investigate a wide range of techniques for text understanding – ranging from representation learning and distributional semantics all the way through symbolic, entity-based approaches leveraging wide-coverage knowledge graphs – and apply these to a wide range of research topics such as such computational semantics, multilinguality, information retrieval and multimodal NLP, to name a few.
Here is a short video that summarizes (in German and for the general public) some of the things that what we do in our group.
People
Faculty:
Staff:
- Tommaso Green
- Chia-Chien Hung
- Christopher Klamm
- Ines Rehbein
- Ines Reinig
- Daniel Ruffinelli
- Sotaro Takeshita
- Tornike Tsereteli
Alumni (only first post-DWS station):
- Fabian David Schmidt (PhD student at Uni Würzburg)
- Laura Dietz (Assistant Professor at the University of New Hampshire)
- Stefano Faralli (Assistant Professor at Unitelma Sapienza Roma)
- Goran Glavaš (Professor at CAIDAS Würzburg)
- Anne Lauscher (Post-doc at DMI Bocconi)
- Robert Litschko (Post-doc at LMU Munich)
- Federico Nanni (Research Data Scientist at the Alan Turing Institute)
- Pedro Ortiz Suarez (Researcher at the Speech and Language Technology Team at DFKI GmbH Berlin)
- Petar Ristoski (Applied Researcher at Ebay)
- Marco Rovera (Post-doc at HDM Stuttgart)
- Michael Schuhmacher (R&D Data and Knowledge Architect at BASF)
- Sanja Stajner (Senior Research Scientist at Symanto Research GmbH)
- Dmitry Ustalov (Research Scientist at Yandex)
- Lydia Weiland (Senior specialist for Data Science und AI at DB Systel GmbH)
Projects
- VAriable Detection, Interlinking and Summarization (DFG)
- Automatic detection of populist rhetoric in text (RiSC Programm MWFK BaWü)
- UNCOVER: Uncovering ideological frames in political discourses (DFG)
Completed
- JOIN-T 2: Joining graph- and vector-based sense representations for semantic end-user information access (DFG)
- SFB 884: Political Economy of Reforms (DFG)
- EUINACTION: Willingness and Capacity for EU Policy Action in Times of Crisis: Conflicts, Positions and Outcomes (NORFACE/DFG)
- JOIN-T: Joining Ontologies and semantics INduced from Text (DFG)
- Part-Time Master Program: Data Science (MWFK BaWü)
- Algebraic Reasoning over Events from Text and External Knowledge (Eliteprogramm für Postdocs, BW Stiftung)
- Knowledge consolidation and organization for query-specific Wikipedia construction (Eliteprogramm für Postdocs, BW Stiftung)
- Deep semantic models for high-end NLP applications (Juniorprofessorenprogramm MWFK BaWü)
- Vision and language understanding beyond literal meaning (RiSC Programm MWFK BaWü)