Welcome to the Language Technology Lab

Covid-19 Info:
Please refer to our teaching page for more information about the teaching situation during the winter semester.

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:

Educational NLP

  • 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 language
  • Semantic meaning relations

NLP Engineering

  • 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.

Marie Bexte wins GSCL Award for best Student Thesis

Marie Bexte won the GSCL Award for the best Student Thesis for her master thesis "Combined Analysis of Image and Text Using Visio-Linguistic Neural Models - A Case Study on Robustness Within an Educational Scoring Task". The price was awarded at this year's KONVENS in Düsseldorf. Congratulations, Marie!

Ronja Laarmann-Quante receives KlarText Award

Ronja Laarmann-Quante receives the KlarText Award for science communication by the Klaus Tschira foundation. Every year, young researchers across Germany are invited to present the key findings of their dissertation in an easy to understand manner to the general public. Ronja received this year's award in the computer science category for the article "Schwere Radieschencreme" about the automatic classification of spelling errors in texts by elementary school students. Congratulations, Ronja!

Paper accepted at The First Workshop on Understanding Implicit and Underspecified Language

The following paper has been accepted at The First Workshop on Understanding Implicit and Underspecified Language:
Marie Bexte, Andrea Horbach and Torsten Zesch: Implicit Phenomena in Short-answer Scoring Data

Paper accepted at ICDAR2021

The following paper has been accepted at ICDAR2021:
Christian Gold, Dario van den Boom and Torsten Zesch: Personalizing Handwriting Recognition Systems with Limited User-Specific Samples.