Cross-Lingual Summarization for Overseas Applications Using Multilingual Pre-Trained Models and Knowledge Distillation

Cross-lingual summarization (CLS) has emerged as an essential tool for bridging linguistic gaps in global communication, facilitating the extraction of concise and meaningful content in a target language from source documents written in different languages. This work introduces a novel framework for CLS, leveraging state-of-the-art multilingual pre-trained models alongside knowledge distillation techniques to ensure efficient and scalable performance. The approach is built on transformer-based architectures, such as mBART and mT5, which are fine-tuned to address the challenges of semantic coherence, fluency, and context preservation across diverse language pairs. To optimize these models for deployment in resource-constrained environments, knowledge distillation is employed, transferring knowledge from larger, computationally expensive models to lightweight student models while maintaining high accuracy. Extensive experimentation on multilingual datasets showcases the robustness of the proposed method, achieving significant improvements over traditional pipeline approaches that rely on separate translation and summarization steps. Evaluation metrics, including ROUGE and BLEU scores, demonstrate superior performance across multiple language pairs. Moreover, the proposed framework achieves a threefold reduction in computational overhead compared to full-scale transformer models, making it highly suitable for real-world overseas applications. This research provides a scalable, efficient, and effective solution for generating high-quality summaries across languages, contributing to enhanced multilingual accessibility and information sharing on a global scale.