DOC: Improving Long Story Coherence With Detailed Outline Control

Kevin Yang, Dan Klein, Nanyun Peng, Yuandong Tian

Main: Generation Main-poster Paper

Poster Session 6: Generation (Poster)
Conference Room: Frontenac Ballroom and Queen's Quay
Conference Time: July 12, 09:00-10:30 (EDT) (America/Toronto)
Global Time: July 12, Poster Session 6 (13:00-14:30 UTC)
Keywords: text-to-text generation
TLDR: 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...
You can open the #paper-P679 channel in a separate window.
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.