I am a Research Fellow at the Research Group in Computational Linguistics (RGCL) at the University of Wolverhampton (UK).
Before coming to Wolverhampton, I spent seven years holding research and teaching positions in Germany at the University of Cologne, at Saarland University, and at the German Research Center for Articial Intelligence (DFKI). I received my PhD from Saarland University with a thesis on computational methods applied to varieties of pluricentric languages. I have degrees in Information Systems (B.Sc.), Translation Studies (Pg.Dip.), and Natural Language Processing (M.A.).
My research focuses on the application of computational methods to large bodies of texts. My research interests include language and dialect variation, second language acquisition and educational NLP applications, forensic linguistics, author profiling, text categorization, machine translation and translation technology. Here is a complete list of my publications and the language resources I've developed.
I am one of the organizers of the series of workshops on NLP for Similar Languages, Varieties and Dialects (VarDial). The next edition is VarDial 2018 at COLING in Santa Fe, USA. I am co-editing with Preslav Nakov a book for the series Studies in Natural Language Processing and a special issue of the journal Natural Language Engineering on the same topic. Both publications by Cambridge University Press.
Previously, I co-organized the second Complex Word Identification (CWI) shared task at the BEA workshop, the shared task on Aggression Identification in Social Media, the TRAC workshop, and the Automatic Post Editing (APE) task at WMT. I co-edited a volume on Non-standard Data Sources in Corpus-based Research.
I am a program committee member of several workshops and conferences. A list is available here.