先翻译还是先简化：对英法双语文本简化进行的分析
Translate or Simplify First: An Analysis of Cross-lingual Text Simplification in English and French
AI总结：
本文研究了英语和法语间跨语言文本简化的方法，通过不同提示策略评估其效果，发现翻译后简化方法在简洁性上表现最佳。
摘要：
跨语言文本简化（CLTS）旨在通过同时处理语言复杂性和翻译来提高内容的可及性。本研究通过大型语言模型（LLMs）评估了不同提示策略在英法之间CLTS的有效性。我们考察了五种不同的提示系统：一种直接提示LLM同时执行翻译和简化，两种组合方法（翻译后简化或简化后翻译），以及两种分解方法（在单独连续提示中执行相同操作）。这些系统在五个不同体裁的语料库（维基百科和医学文本）上使用七种最先进的LLMs进行评估。输出质量通过包含自动指标、全面的语言特征分析和人类评估（简洁性和意义保持）的多维评估框架进行评估。我们的发现表明，虽然直接提示始终获得最高的BLEU分数，表明意义保真度，翻译后简化方法在简洁性上表现最佳，如通过语言特征测量。
英文摘要：
Cross-Lingual Text Simplification (CLTS) aims to make content more accessible across languages by simultaneously addressing both linguistic complexity and translation. This study investigates the effectiveness of different prompting strategies for CLTS between English and French using large language models (LLMs). We examine five distinct prompting systems: a direct prompt instructing the LLM to perform both translation and simplification simultaneously, two Composition approaches that either translate-then-simplify or simplify-then-translate within a single prompt, and two decomposition approaches that perform the same operations in separate, consecutive prompts. These systems are evaluated across a diverse set of five corpora of different genres (Wikipedia and medical texts) using seven state-of-the-art LLMs. Output quality is assessed through a multi-faceted evaluation framework comprising automatic metrics, comprehensive linguistic feature analysis, and human evaluation of simplicity and meaning preservation. Our findings reveal that while direct prompting consistently achieves the highest BLEU scores, indicating meaning fidelity, Translate-then-Simplify approaches demonstrate the highest simplicity, as measured by the linguistic features.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
