Chinese sentence simplification faces challenges due to the lack of large-scale labeled parallel corpora and the prevalence of idioms. To address these challenges, we propose Readability-guided Idiom-aware Sentence Simplification (RISS), a novel framework that combines data augmentation techniques with lexcial simplification. RISS introduces two key components: (1) Readability-guided Paraphrase Selection (RPS), a method for mining high-quality sentence pairs, and (2) Idiom-aware Simplification (IAS), a model that enhances the comprehension and simplification of idiomatic expressions. By integrating RPS and IAS using multi-stage and multi-task learning strategies, RISS outperforms previous state-of-the-art methods on two Chinese sentence simplification datasets. Furthermore, RISS achieves additional improvements when fine-tuned on a small labeled dataset. Our approach demonstrates the potential for more effective and accessible Chinese text simplification.
@article{arxiv.2406.02974,
title = {Readability-guided Idiom-aware Sentence Simplification (RISS) for Chinese},
author = {Jingshen Zhang and Xinglu Chen and Xinying Qiu and Zhimin Wang and Wenhe Feng},
journal= {arXiv preprint arXiv:2406.02974},
year = {2024}
}
Comments
Accepted to the 23rd China National Conference on Computational Linguistics (CCL 2024)