Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training
This work addresses the challenge of limited parallel data for text simplification in non-English languages like German, offering a method to enhance accessibility, though it is incremental as it builds on existing pre-training techniques.
The paper tackled the problem of parallel data scarcity for German text simplification by proposing a two-step approach using style-specific pre-training on German Easy Language, which reduced the required parallel data and improved performance on downstream tasks.
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.