论文标题
小红帽在全球环游：跨语言的故事计划和发电大型语言模型
Little Red Riding Hood Goes Around the Globe:Crosslingual Story Planning and Generation with Large Language Models
论文作者
论文摘要
以前的工作证明了在主要集中于英语的单语言环境中计划创建故事的有效性。我们考虑计划是否会带来跨语言自动故事的优势。我们提出了一项新的任务，即通过计划进行跨语性故事生成，并为此任务提供一个新的数据集。我们通过利用大型预训练的语言模型的创造性和推理能力来对不同计划进行全面研究，并以几种语言的形式产生故事。我们的结果表明，将故事构成三个行为的计划导致了更连贯和有趣的叙述，同时允许明确控制其内容和结构。
Previous work has demonstrated the effectiveness of planning for story generation exclusively in a monolingual setting focusing primarily on English. We consider whether planning brings advantages to automatic story generation across languages. We propose a new task of cross-lingual story generation with planning and present a new dataset for this task. We conduct a comprehensive study of different plans and generate stories in several languages, by leveraging the creative and reasoning capabilities of large pre-trained language models. Our results demonstrate that plans which structure stories into three acts lead to more coherent and interesting narratives, while allowing to explicitly control their content and structure.
