English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose the task of outline-conditioned story generation: given an outlineas a set of phrases that describe key characters and events to appear in astory, the task is to generate a coherent narrative that is consistent with theprovided outline. This task is challenging as the input only provides a roughsketch of the plot, and thus, models need to generate a story by interweavingthe key points provided in the outline. This requires the model to keep trackof the dynamic states of the latent plot, conditioning on the input outlinewhile generating the full story. We present PlotMachines, a neural narrativemodel that learns to transform an outline into a coherent story by tracking thedynamic plot states. In addition, we enrich PlotMachines with high-leveldiscourse structure so that the model can learn different writing stylescorresponding to different parts of the narrative. Comprehensive experimentsover three fiction and non-fiction datasets demonstrate that large-scalelanguage models, such as GPT-2 and Grover, despite their impressive generationperformance, are not sufficient in generating coherent narratives for the givenoutline, and dynamic plot state tracking is important for composing narrativeswith tighter, more consistent plots.

PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking