Skip to content

HIIG at GermEval 2022: Best of Both Worlds Ensemble for Automatic Text Complexity Assessment

Author: Asghari, H. & Hewett, F.
Published in: Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text, 15–20
Year: 2022
Type: Academic articles

In this paper we explain HIIG’s contribution to the shared task Text Complexity DE Challenge 2022. Our best-performing model for the task of automatically determining the complexity level of a German-language sentence is a combination of a transformer model and a classic feature-based model, which achieves a mapped root square mean error of 0.446 on the test data.

Visit publication
Download Publication


Connected HIIG researchers

Hadi Asghari, Dr.

Researcher: AI & Society Lab

Freya Hewett

Researcher: AI & Society Lab

  • Open Access
  • Peer Reviewed

Related projects