Portrait and Research Interests
I am senior lecturer (Privatdozent) and postdoc staff member in Computational Linguistics (CL) at the Department of Computational Linguistics and leader of the platform Text Crunching Center (TCC), which offers computational linguistics services to the University and other partners.
I have been senior lecturer and computing scientist (wissenschaftlicher Informatiker) at the English Department of the University of Zurich (Gerold Schneider's homepage at the English Department).
My research interests include corpus linguistics, semantic mining, automated media content analysis, cognitive linguistics, digital humanities, robust parsing, syntax, formal grammar.
I am involved in research on automated media content analysis, and on Text Mining in the biomedical and many other domains. I am also doing research on Digital Humanities, learner language, variationist linguistics (genre, regions, contrastive, typology), and statistical methods.
I have published over 110 peer-reviewed articles and a coursebook on Statistics.
In the winter term 2017/18 I have worked as Substituting Professor for German Linguistics at TU Dortmund University.
I have worked at the linguistics department of University of Konstanz, substituting Prof. Dr. Miriam Butt from 2015 to 2017 as Professor of Computational and General Linguistics.
Selected articles in bibliographical databases can be
downloaded from ZORA
or downloaded from my Google Scholar profile
I have written my cumulative habilitation on using computational linguistics methods for descriptive linguistics, text mining and psycholinguistics.
I have written a a low-complexity, broad-coverage probabilistic Dependency Parser for English,as a part of
I have also ported it to German, together with Rico Sennrich.
My Recent Publications related to the Department of Computational Linguistics (ZORA)
My Recent Publications related to the English Department (ZORA)
My research interests iclude
- Natural Language Processing (NLP)
- Corpus Linguistics
- Robust Fast Broad-Coverage Parsing
- Dependency Grammar
- Text Mining, Information Extraction
- Semantic Web
- Information Retrieval
- BioMedical Parsing Applications
- Automated Media Content Analysis
- Formal Grammar
My interests also include UNIX and Mac OS X system administration, Prolog and Perl programming, desktop publishing, travelling, literature, jogging and cycling. I have taught Prolog, theoretical computing science, and semantic web at Fernfachhochschule Schweiz (Swiss distance learning UAS). I have taught Prolog and Perl at the CL department of the University of Geneva.
Dependency Grammar and Robust Parsing
I have written a low-complexity, broad-coverage probabilistic Dependency Parser for English, Pro3Gres, as part of my doctoral thesis.
I have written my Master's Paper on Dependency Grammar and the partly dependency-based Link Grammar. I am currently developing Pro3Gres: a robust, probabilistic parser for a Dependency Grammar. In winter 2003/2004 and winter 2005/2006 I am teaching Dependency Grammar Parsing. In winter 2006/2007/2014 I am teaching Parsing Technology.
Both the English Seminar and the Department of Computational Linguistics have a long tradition in Corpus Linguistics research. I am a member of the Archer consortium. At the English Department, I am involved in the compilation of and web interface access to several corpora. In summer 2003, I teach a seminar on Corpus Linguistics. In summer 2006, I teach a colloquium on Corpus Linguistics. In spring 2008, I teach a lecture on Corpus Linguistics, together with Fabio Rinaldi. In spring 2008, I teach the workshop at the ICAME conference, together with Hans Martin Lehmann and Nelleke Oostdjik. In autumn 2012, I teach a BA seminar on Corpus Linguistics.
BioMedical Parsing and Relation Finding
Our research on an important application of my high-precision robust parser has started in 2005, and is an NFS project from 2008 to 2013. OntoGene: Relation Finding in the BioMedical domain.