Welcome to the Language Technology Lab
The language technology lab at the University of Duisburg-Essen is a part of the division of Computer Science and Applied Cognitive Sciences at the Faculty of Engineering.
We conduct research in the field of language technology and natural language processing.
We strongly believe that engineering is a key part of research in this field and that often a new insight is only to be found when re-implementing an approach.
We are especially interested in analyzing and processing non-standard, error-prone language as found in social media and learner language.
Consequently, our research can be divided into three main areas:
- Short answer scoring
- Essay scoring
- Vocabulary acquisition
- Spelling and grammar correction
- Exercise generation
- Exercise difficulty prediction
Social Media Analysis
- Sentiment and stance detection
- Argument mining
- Detection of hate speech and abusive languag
- Semantic meaning relations
- Robustness of tools
- Domain adaption
- Large-scale semantic processing
We are committed to reproducible and replicable research. We generally make all research software publicly available. Thus, we develop and maintain multiple open-source software projects.
Paper accepted at LAW XIII 2019
The following paper has been accepted at the LAW XIII 2019 workshop in Florence, Italy, which is colocated with ACL 2019:
Darina Gold, Venelin Kovatchev, and Torsten Zesch: Annotating and analyzing the interactions between meaning relations.
Paper accepted for 'Frontiers in Education'
The following paper has been accepted for the Journal "Frontiers in Education":
Andrea Horbach, Torsten Zesch: The Influence of Variance in Learner Answers on Automatic Content Scoring*, Frontiers in Education Jg. 4 (2019) S. 28
Paper accepted at SemEval 2019
We have two papers accepted at the SemEval 2019 workshop in Minneapolis, USA, which is colocated with NAACL-HLT 2019.
Piush Aggarwal, Tobias Horsmann, Michael Wojatzki and Torsten Zesch: LTL-UDE at SemEval-2019 Task 6: BERT and Two-Vote Classification for Categorizing Offensiveness
Huangpan Zhang, Michael Wojatzki, Tobias Horsmann and Torsten Zesch: ltl.uni-due at SemEval 2019 Task 5: Simple but Effective Lexico-Semantic Features for Detecting Hate Speech in Twitter
Paper accepted at NAACL-HLT 2019
The following interdisciplinary paper has been accepted at the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) in Minneapolis, USA.
Frederike Zufall, Tobias Horsmann and Torsten Zesch: From legal to technical concept: Towards an automated classification of German political Twitter postings as criminal offenses