Prof. Dr.-Ing. Torsten Zesch

Tel: +49 (0)203 379-2006
Office: LE 411

Research Interests

  • Educational Natural Language Processing
    • Exercise Generation / Difficulty Prediction
    • Automated Scoring
    • L1-Influence
  • Social Media Analysis
    • Stance Detection
    • Robust Pre-processing
  • Language Technlogy Infrastructure
    • Replicablity / Reproducibility

Short Bio

  • 2014 - Appointed Professor of Language Technology at University of Duisburg-Essen, Germany
  • 2013 - Substitute Professor (Vertretungsprofessur) “Language Technology”, University of Duisburg-Essen, Germany
  • 2012 - Substitute Professor (Vertretungsprofessur) “Knowledge Mining & Assessment”, German Institute for International Educational Research (DIPF), Frankfurt, Germany
  • 2009 - Dr.-Ing. degree from Technische Universität Darmstadt, Germany
  • 2005 - Diploma in computer science from the Chemnitz University of Technology, Germany.

Professional Activities

Selected Projects

Organization of Events

Selected Talks

  • Upcoming - May 2018: Keynote at EALTA 2018
  • January 2017: Invited Talk TestDaF Institut, Ruhr-Universität Bochum - "Sprachtechnologische Ansätze zur zielgerichteten Generierung von Sprachlern- und Sprachtestitems"
  • May 2016: Keynote at Workshop on “Normalisation and Analysis of Social Media Texts (NormSoMe)” at LREC, Portoroz, Slovenia - „Your noise is my research question! - Limitations of normalizing social media data”
  • October 2015: Invited Talk - Centre for Language Technology, Göteborg, Schweden. Presentation at the 6th annual workshop of the CLT
  • August 2014: Invited Talk - Educational Testing Service (ETS), Princeton, USA - “Automatically Determining the Difficulty of the C-Test Language Proficiency Test”


6 results
[6] The Role of Diacritics in Increasing the Difficulty of Arabic Lexical Recognition Tests
and , In Proceedings of the 7th Workshop on NLP for Computer Assisted Language Learning at SLTC 2018 (NLP4CALL 2018), .

[bibtex] [pdf]
[5] A flexible online system for curating reduced redundancy language exercises and tests
, , and , In Future-proof CALL: language learning as exploration and encounters short papers from EUROCALL 2018 (Peppi Taalas, Juha Jalkanen, Linda Bradley, Sylvie Thouësny, eds.), .

[bibtex] [pdf]
[4] Comparing Target Sets for Stance Detection: A Case Study on YouTube Comments on Death Penalty
and , In Proceedings of the Conference on Natural Language Processing (KONVENS), .

[bibtex] [pdf]
[3] Do Women Perceive Hate Differently: Examining the Relationship Between Hate Speech, Gender, and Agreement Judgments
, , and , In Proceedings of the Conference on Natural Language Processing (KONVENS), .

[bibtex] [pdf]
[2] Agree or Disagree: Predicting Judgments on Nuanced Assertions
, , and , In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics (*SEM), .

[bibtex] [pdf]
[1] Quantifying Qualitative Data for Understanding Controversial Issues
, , and , In Proceedings of the Language Resources and Evaluation Conference (LREC), .

[bibtex] [pdf]