Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training

TL;DR

This paper presents a method for German text simplification that leverages style-specific pre-training of language models to overcome the scarcity of parallel data, resulting in more accessible texts with less training data.

Contribution

It introduces a two-step approach using style-specific pre-training to improve German text simplification and reduce the need for extensive parallel datasets.

Findings

Pre-trained models adapt to Easy Language style characteristics.

Reduced parallel data needed for effective simplification.

Improved accessibility of German texts through style-specific pre-training.

Abstract

Automatic text simplification systems help to reduce textual information barriers on the internet. However, for languages other than English, only few parallel data to train these systems exists. We propose a two-step approach to overcome this data scarcity issue. First, we fine-tuned language models on a corpus of German Easy Language, a specific style of German. Then, we used these models as decoders in a sequence-to-sequence simplification task. We show that the language models adapt to the style characteristics of Easy Language and output more accessible texts. Moreover, with the style-specific pre-training, we reduced the number of trainable parameters in text simplification models. Hence, less parallel data is sufficient for training. Our results indicate that pre-training on unaligned data can reduce the required parallel data while improving the performance on downstream tasks.