Welcome to the Language Technology Lab

The language technology lab carries out research in the field of Natural Language Processing. We mainly focus on two areas of specialization:

Educational NLP

  • Short answer scoring
  • Essay scoring
  • Vocabulary Acquisition
  • Spelling and grammar correction

Social Media Analysis

  • Robustness of tools
  • Domain adaption
  • Large-scale semantic processing

We are committed to reproducible and replicable research. Thus, we generally make all research software publicly available.

Four papers accepted for LREC 2018

We got four papers accepted for next year's LREC 2018 in Miyazaki, Japan:

  • Michael Wojatzki, Saif M. Mohammad, Torsten Zesch, and Svetlana Kiritchenko: Quantifying Qualitative Data for Understanding Controversial Issues
  • Tobias Horsmann and Torsten Zesch: DeepTC -- An Extension of DKPro Text Classification for Fostering Reproducibility of Deep Learning Experiments
  • Torsten Zesch and Andrea Horbach: ESCRITO - An NLP-Enhanced Educational Scoring Toolkit
  • Andrea Horbach and Manfred Pinkal: Semi-Supervised Clustering for Short Answer Scoring

GermEval 2017

Together with the Language Technology Group (LT) from the University Hamburg, we have organized GermEval 2017 – Shared Task on Aspect-based Sentiment in Social Media Customer Feedback. In this shared task, we utilized one of the largest datasets among all so-far conducted shared tasks on Sentiment Analysis. The shared task was framed as aspect-based sentiment analysis with four sub tasks: Relevance, Document Sentiment, Aspect-based Sentiment and Opinion Target Extraction.

The proceedings are available on the website. The task description can be found below:

GermEval 2017: Shared Task on Aspect-based Sentiment in Social Media Customer Feedback (Michael Wojatzki, Eugen Ruppert, Sarah Holschneider, Torsten Zesch and Chris Biemann)

Paper accepted at NLPTEA 2017

The following paper has been accepted for the 4th Workshop on NLP Techniques for Educational Applications (NLPTEA 2017), in Taipei, Taiwan:

  • Andrea Horbach, Yuning Ding and Torsten Zesch: The Influence of Spelling Error on Content Scoring Performance.

Paper accepted in JLCL- Special Issue on NLP for Arabic 2017

The following paper has been accepted in the Journal of Language Technology and Computational Linguistics, JLCL Volume 32 (2017), Issue 1: NLP for Arabic/Perso alphabets.

  • Osama Hamed and Torsten Zesch: A Survey and Comparative Study of Arabic Diacritization Tools.