An Approach towards Unsupervised Text Simplification on Paragraph-Level for German Texts

Leon Fruth, Robin Jegan, Andreas Henrich


Abstract
Text simplification as a research field has received attention in recent years for English and other languages, however, German text simplification techniques are lacking thus far. We present an unsupervised simplification approach for German texts using reinforcement learning (self-critical sequence training). Our main contributions are the adaption of an existing method for English, the selection and creation of German corpora for this task and the customization of rewards for particular aspects of the German language. In our paper, we describe our system and an evaluation, including still present issues and problems due to the complexity of the German language, as well as directions for future research.
Anthology ID:
2024.determit-1.8
Volume:
Proceedings of the Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Giorgio Maria Di Nunzio, Federica Vezzani, Liana Ermakova, Hosein Azarbonyad, Jaap Kamps
Venues:
DeTermIt | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
77–89
Language:
URL:
https://aclanthology.org/2024.determit-1.8
DOI:
Bibkey:
Cite (ACL):
Leon Fruth, Robin Jegan, and Andreas Henrich. 2024. An Approach towards Unsupervised Text Simplification on Paragraph-Level for German Texts. In Proceedings of the Workshop on DeTermIt! Evaluating Text Difficulty in a Multilingual Context @ LREC-COLING 2024, pages 77–89, Torino, Italia. ELRA and ICCL.
Cite (Informal):
An Approach towards Unsupervised Text Simplification on Paragraph-Level for German Texts (Fruth et al., DeTermIt-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.determit-1.8.pdf