Kontakt
Pfaffenwaldring 5 b
70569 Stuttgart
Deutschland
Raum: 02.017
Projects running in 2016
- Terminology extraction and ontology construction (10/2014 - 11/2016, cooperation with Robert Bosch GmbH, Corporate Research), on techniques for term extraction, its evaluation and its use for the creation of domain-specific resources
- SFB 732, B3 (2006-1014 (PI since 10/2011: Prof. Jonas Kuhn))
- TTC: Terminology extraction, translation tools and comparable corpora
(EU: FP-7, STREP 248005, 01/2010 - 12/2012) on data extraction from comparable corpora
Coordinator: Beatrice Daille, University of Nantes
Collaborators: Anita Ramm, Marioin Weller - WordGraph: Using graph-based methods for investigating lexical semantics on the basis of corpora (second phase: 2011 - 2013, Coord.: Hinrich Schuetze, cf. StatNLP Research Overview)
- Creation of a corpus infrastructure for Sepedi (Northern Sotho) : cooperation with Prof. Dr. Daan J. Prinsloo, University of Pretoria, Dept. of African Languages (2003-2010)
- Developing a Model for electronic Dictionaries (2005-2008)
(partly financed by Stias, Stellenbosch Institute for Advanced Study, Stellenbosch, South Africa)
Projects at University of Hildesheim
- Computational linguistic control and enhancement of the linguistic quality of requirements (08/2014 - 11/2016), in cooperation with Daimler AG, RD/EIT.
- e-Identity (05/2012 -- 04/2015)
Cooperation with Prof. Dr. Cathleen Kantner (Univ. of Stuttgart, Political Sciences, Coordinator), Prof. Dr. Jonas Kuhn (Univ. of Stuttgart, IMS) and Prof. Dr. Manfred Stede (Univ. of Potsdam): Using computational linguistic techniques to support political scientists in text interpretation - SeLA, Scientific e-Lexicography for Africa, (06/2012 -- 05/2015)
Cooperation with University of South Africa, University of Pretoria, University of Stellenbosch and University of Namibia, on methods for the preparation of electronic dictionaries. - Vergleich von maschineller und manueller Termextraktion
(cooperation with an industrial partner) (2011-2013) - New electronic versions of the Dictionary of South African English (04/2015-12/2015), on turning a historical-scholarly dictionary into a data collection for multiple selective queries.
Selected past projects: lexicons, corpora, morphology
- Speaker function in the workgroup NA-105-AA-06 of DIN(German Standard Institute), on standards for language resources (mirror committee of ISO TC 37 SC 4).
- Collocations en Contexte, 03/2006 - 02/2008, partly financed by AUF, Agence Universitaire pour la Francophonie, coord. Prof. Amalia Todirascu (Univ. of Strasbourg)
- DFG- Transferbereich TFB-32: Automatische Exzerption:Tools and methods for building and upgrading dictionaries on the basis of text corpora (10/2001 - 10/2003)
- DECIDE (Designing and Evaluating Extraction Tools for Collocations in Dictionaries and Corpora,
EU MLAP 93/19, 1994 - 1996) - DeKo (Deutsche Derivations- und Kompositionsmorphologie) (1999 - 2001, Linguistic work towards a German computational morphology system for inflection, derivation and compounding, based on the SFST system developed by Helmut Schmid )
- TextCorpora and tools for their exploration Project on corpus processing techniques which produced, among others, the corpus query tool IMS CorpusWorkbench, CWB
- DELIS (Descriptive Lexical Specifications and Tools for corpus-based Lexicon Building,
EU LRE 61.034, coordinator) - Several application-oriented projects with publishing houses from Germany, Denmark and the Netherlands, concerning the extraction of lexicographically relevant linguistic data (collocations, examples, subcategorization data, etc.) from text corpora
Selected past projects: dialogue systems
- NITE (Natural Interactivity Tools Engineering, 1.4.2001 - 31.7.2003)
- ISLE - International Standards for Language Engineering
- MATE - Multilevel Annotation, Tools Engineering
- DISC and DISC2 - Dialogue Systems and Components
Selected past projects: infrastructure and standardization
- D-SPIN: Deutsche Sprachressourcen-Infrastruktur (09/2008 - 03/2011, coordinated by Prof. Dr. E.Hinrichs , University of Tuebingen, local responsables at IMS: Prof. Dr. H.Schuetze, PD Dr. H. Schmid, U. Heid)
- EAGLES (Expert Advisory Group on Linguistic Engineering Standards)
- ISLE - International Standards for Language Engineering
- ELSNET (European Network of Excellence in Speech and Natural Language Processing - Managing Node for Germany)
- Eurotra-7 Study on Reusable Lexical and Terminological Resources for NLP (coordinator)
- RELATOR (A European Network of Repositories for Linguistic Resources, EU LRE 62.056)