arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.16667cs.CL
收藏

一种通过想象实现的以角色为中心的创意故事生成方法

A Character-Centric Creative Story Generation via Imagination

Seoul National University(首尔大学)

Kyeongman Park, Minbeom Kim, Kyomin Jung

AI总结:

针对现有故事生成方法多样性与角色深度不足的问题,提出含图像引导想象、多作者模型的CCI框架,经多维度评估验证其提升故事创造力的效果,还支持交互式多模态生成,拓展了人-大模型融合的文化应用方向。

摘要:

创意故事生成长期以来都是自然语言处理(NLP)研究的目标。现有方法虽致力于生成长篇连贯的故事,但在多样性和角色深度方面远不及人类水平。为解决这一问题,我们提出了一种名为CCI(Character-centric Creative story generation via Imagination,基于想象的以角色为中心的创意故事生成)的新型故事生成框架。CCI包含两个服务于创意故事生成的模块:IG(Image-Guided Imagination,图像引导想象)模块和MW(Multi-Writer model,多作者模型)模块。在IG模块中,我们利用文本生成图像模型,以比纯文本方法更新颖、更具体的方式生成角色、背景、主要情节等关键故事元素的视觉表征。MW模块利用这些故事元素生成多个角色描述候选,并选择最优描述插入故事中,从而增强叙事的丰富性与深度。我们通过统计分析、人类评估及大语言模型(LLM)评估,对比了CCI与基线模型生成的故事。结果表明,IG和MW模块显著提升了故事创造力的多个维度。此外,我们的框架支持与用户进行交互式多模态故事生成,为人类与大语言模型融合助力文化发展开辟了新可能。项目主页:https://www.2024cci.p-e.kr/

英文摘要:

Creative story generation has long been a goal of NLP research. While existing methodologies have aimed to generate long and coherent stories, they fall significantly short of human capabilities in terms of diversity and character depth. To address this, we introduce a novel story generation framework called CCI (Character-centric Creative story generation via Imagination). CCI features two modules for creative story generation: IG (Image-Guided Imagination) and MW (Multi-Writer model). In the IG module, we utilize a text-to-image model to create visual representations of key story elements, such as characters, backgrounds, and main plots, in a more novel and concrete manner than text-only approaches. The MW module uses these story elements to generate multiple persona-description candidates and selects the best one to insert into the story, thereby enhancing the richness and depth of the narrative. We compared the stories generated by CCI and baseline models through statistical analysis, as well as human and LLM evaluations. The results showed that the IG and MW modules significantly improve various aspects of the stories' creativity. Furthermore, our framework enables interactive multi-modal story generation with users, opening up new possibilities for human-LLM integration in cultural development. Project page : https://www.2024cci.p-e.kr/

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。

↑