Exploring Automatic Text Simplification of German Narrative Documents

Thorben Schomacker, Tillmann Dönicke, Marina Tropmann-Frick
12/15/2023
cs.CLcs.AI

No official code found. Best implementation: tschomacker/aligned-narrative-documents (3 stars, CC-BY-4.0, last commit 2023-09-16).

Abstract

In this paper, we apply transformer-based Natural Language Generation (NLG) techniques to the problem of text simplification. Currently, there are only a few German datasets available for text simplification, even fewer with larger and aligned documents, and not a single one with narrative texts. In this paper, we explore to which degree modern NLG techniques can be applied to German narrative text simplifications. We use Longformer attention and a pre-trained mBART model. Our findings indicate that the existing approaches for German are not able to solve the task properly. We conclude on a few directions for future research to address this problem.

View on arXivView PDF

Code Implementations(1)

tschomacker/aligned-narrative-documentsCommunity100%
CC-BY-4.0

A collection of scripts to create a Document-aligned corpus of German Narrative Texts from four different sources of Simple Language Texts and three different sources of Standard Language Texts.

31PythonJan 19, 20233 years agoCC-BY-4.0
datasetgerman-languagenlp

Similar Papers

SimpLex: a lexical text simplification architecture

84% match1 repo32023

Can Knowledge Graphs Simplify Text?

84% match1 repo112023

ARTIST: ARTificial Intelligence for Simplified Text

83% match2023

Context-Aware Document Simplification

83% match1 repo72023

MCTS: A Multi-Reference Chinese Text Simplification Dataset

83% match1 repo362023

A Novel Dataset for Financial Education Text Simplification in Spanish

82% match2023

Cite this paper

@article{schomacker2023exploring,
  title  = {Exploring Automatic Text Simplification of German Narrative Documents},
  author = {Thorben Schomacker and Tillmann Dönicke and Marina Tropmann-Frick},
  year   = {2023},
  eprint = {2312.09907},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.09907v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.09907.svg)](https://codeofpaper.com/paper/2312.09907)

Discussion