DOC: Improving Long Story Coherence With Detailed Outline Control
Kevin Yang, Dan Klein, Nanyun Peng, Yuandong Tian

TL;DR
The paper introduces the DOC framework that enhances long story coherence by using a detailed outline and controller, significantly improving plot consistency, relevance, and interestingness in automated story generation.
Contribution
It presents a novel hierarchical outline and control mechanism that shifts creative planning to the outline stage, leading to more coherent long-form stories.
Findings
22.5% absolute gain in plot coherence
28.2% improvement in outline relevance
20.7% increase in story interestingness
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Artificial Intelligence in Games
MethodsALIGN
