首页|基于三幕结构思维链和语义自洽的事件驱动故事生成方法

基于三幕结构思维链和语义自洽的事件驱动故事生成方法

扫码查看
原文链接
  • 万方数据
  • 维普
事件驱动故事生成旨在根据有限的故事背景和事件信息生成连贯且符合事件内容的故事.然而,现有方法常因对复杂的事件关系推理不足,导致生成的故事存在语义不连贯、情节冲突等问题.为此,文中提出基于三幕结构思维链和语义自洽的事件驱动故事生成方法,在生成故事前选择类型多样的故事示例,学习不同类型故事的写作方式.生成故事时,按照故事的开端、冲突和结局三幕结构设计思维链,引导方法合理规划故事内容,避免故事情节前后矛盾.生成故事后,引入语义自洽,模拟作家的推敲过程,从生成的多个故事中选择语义一致、连贯性和相关性较高的故事.实验表明,相比提示学习方法,文中方法的BLEU-4和BERTScore指标值有所提升,并且在人工评估中也占有一定的优势.
Event-Driven Story Writing Based on Three-Act Structural Chain-of-Thought and Semantic Self-Consistency
Event-driven story writing aims to create coherent stories that conform to event content based on limited background and event information.However,existing methods often suffer from semantic incoherence and plot conflicts due to insufficient reasoning about complex event relationships.To address these problems,a method for event-driven story writing based on three-act structural chain-of-thought and semantic self-consistency is proposed in this paper.Before generating the story,diverse story examples are selected to enable the model to learn different storytelling styles.During the story generation,a chain-of-thought is designed based on three-act structure of setup,confrontation and resolution,guiding the model to reasonably plan the story content and avoid plot inconsistencies.After the story is generated,semantic self-consistency is introduced to simulate the writer's deliberation process,selecting the most semantically consistent,coherent and relevant story from multiple generated versions.Experiments show that the proposed method improves BLEU-4 and BERTScore metrics and demonstrates certain advantages in human evaluations as well.

Event-Driven Story WritingLarge Language ModelSemantic Self-ConsistencyThree-Act Structural Chain-of-Thought

黄于欣、赵源、余正涛、吴磊、马九顺

展开 >

昆明理工大学信息工程与自动化学院 昆明 650504

昆明理工大学云南省人工智能重点实验室 昆明 650504

事件驱动故事生成 大规模语言模型 语义自恰 三幕结构思维链

国家自然科学基金项目国家自然科学基金项目国家自然科学基金项目云南省科技重大专项项目云南省科技重大专项项目云南省基础研究重大专项项目昆明理工大学"双一流"创建联合专项项目

62266027U21B2027U23A20388202302AD080003202303AP140008202401BC070021202201BE070001-021

2024

10.16451/j.cnki.issn1003-6059.202407001

模式识别与人工智能
中国自动化学会,国家智能计算机研究开发中心,中国科学院合肥智能机械研究所

模式识别与人工智能

CSTPCD北大核心
影响因子：0.954
ISSN：1003-6059
年,卷(期)：2024.37(7)
  • 1