NGEP: A Graph-based Event Planning Framework for Story Generation

TL;DR

NGEP is a novel graph-based framework for story event planning that improves narrative coherence and controllability in long text generation by inferring event sequences from an event graph and using a neural event advisor.

Contribution

The paper introduces NGEP, a new graph-based event planning framework that outperforms existing methods in story generation tasks by enhancing coherence and control.

Findings

Outperforms state-of-the-art event planning methods

Improves story coherence and controllability

Enhances downstream story generation quality

Abstract

To improve the performance of long text generation, recent studies have leveraged automatically planned event structures (i.e. storylines) to guide story generation. Such prior works mostly employ end-to-end neural generation models to predict event sequences for a story. However, such generation models struggle to guarantee the narrative coherence of separate events due to the hallucination problem, and additionally the generated event sequences are often hard to control due to the end-to-end nature of the models. To address these challenges, we propose NGEP, an novel event planning framework which generates an event sequence by performing inference on an automatically constructed event graph and enhances generalisation ability through a neural event advisor. We conduct a range of experiments on multiple criteria, and the results demonstrate that our graph-based neural framework outperforms the state-of-the-art (SOTA) event planning approaches, considering both the performance of event sequence generation and the effectiveness on the downstream task of story generation.