Text simplification plays a vital role in natural language processing, yet auto long text simplification remains challenging due to the difficulty in the joint balancing of simplification efficiency and fine-grained quality requirements, such as fluency, grammatical correctness and semantic completeness. To address these challenges, we propose Simplify-Pro, a two-level and progressive LLM-based framework that establishes an effective paradigm for automatic long text simplification under diverse test scenarios. By integrating paragraph-level training, simplification generation, metric-assisted analysis and selective refinement into a unified multi-stage pipeline, our framework achieves superior performance across in-domain and out-of-domain simplification tasks, which matches or even outperforms advanced and proprietary LLMs. Furthermore, comprehensive experiments and qualitative analyses cover the simplification performance, generalization ability and the contribution of each individual stage, demonstrating the effectiveness, robustness and modular design advantages of Simplify-Pro.

By learning the human post-edits, the automatic post-editing (APE) models are often used to modify the output of the machine translation (MT) system to make it as close as possible to human translation. We introduce the system used in our submission of WMT’22 Automatic Post-Editing (APE) English-Marathi (En-Mr) shared task. In this task, we first train the MT system of En-Mr to generate additional machine-translation sentences. Then we use the additional triple to bulid our APE model and use APE dataset to further fine-tuning. Inspired by the mixture of experts (MoE), we use GMM algorithm to roughly divide the text of APE dataset into three categories. After that, the experts are added to the APE model and different domain data are sent to different experts. Finally, we ensemble the models to get better performance. Our APE system significantly improves the translations of provided MT results by -2.848 and +3.74 on the development dataset in terms of TER and BLEU, respectively. Finally, the TER and BLEU scores are improved by -1.22 and +2.41 respectively on the blind test set.