论文标题

DOC:通过详细的轮廓控制改善长话连贯性

DOC: Improving Long Story Coherence With Detailed Outline Control

论文作者

Yang, Kevin, Klein, Dan, Peng, Nanyun, Tian, Yuandong

论文摘要

我们提出了详细的轮廓控制(DOC)框架,以在自动生成数千封长的故事时改善远程情节连贯性。 DOC由两个互补组件组成:一个详细的Outliner和一个详细的控制器。详细的Outliner创建了一个更详细的,层次结构化的轮廓,将创造性的负担从主要的起草过程转移到了计划阶段。详细的控制器可确保通过控制故事段落以与轮廓详细信息保持一致,从而确保在发电期间仍然尊重更详细的轮廓。在对自动产生故事的人类评估中,DOC在情节相干性(22.5%的绝对增益),概述相关性(28.2%)和趣味性(20.7%)上大大优于强烈的RE3基线(Yang等,2022)。人类还认为DOC在交互式生成环境中更具控制性。

We propose the Detailed Outline Control (DOC) framework for improving long-range plot coherence when automatically generating several-thousand-word-long stories. DOC consists of two complementary components: a detailed outliner and a detailed controller. The detailed outliner creates a more detailed, hierarchically structured outline, shifting creative burden from the main drafting procedure to the planning stage. The detailed controller ensures the more detailed outline is still respected during generation by controlling story passages to align with outline details. In human evaluations of automatically generated stories, DOC substantially outperforms a strong Re3 baseline (Yang et al., 2022) on plot coherence (22.5% absolute gain), outline relevance (28.2%), and interestingness (20.7%). Humans also judged DOC to be much more controllable in an interactive generation setting.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源