A New Dataset and Empirical Study for Sentence Simplification in Chinese
This work addresses a data gap for Chinese language learners and children, but it is incremental as it focuses on dataset creation and empirical testing rather than novel method development.
The paper tackles the lack of data for Chinese sentence simplification by introducing the CSS dataset, and it evaluates various methods including Large Language Models on this dataset.
Sentence Simplification is a valuable technique that can benefit language learners and children a lot. However, current research focuses more on English sentence simplification. The development of Chinese sentence simplification is relatively slow due to the lack of data. To alleviate this limitation, this paper introduces CSS, a new dataset for assessing sentence simplification in Chinese. We collect manual simplifications from human annotators and perform data analysis to show the difference between English and Chinese sentence simplifications. Furthermore, we test several unsupervised and zero/few-shot learning methods on CSS and analyze the automatic evaluation and human evaluation results. In the end, we explore whether Large Language Models can serve as high-quality Chinese sentence simplification systems by evaluating them on CSS.