Event Transition Planning for Open-ended Text Generation
This addresses the problem of neural models struggling with causality and event relations in open-ended text generation for applications like dialogue and story completion, representing an incremental improvement.
The paper tackles the challenge of generating coherent and diverse continuations in open-ended text generation tasks by proposing a two-stage method that explicitly arranges ensuing events, resulting in improved text quality in coherence and diversity as demonstrated in experiments.
Open-ended text generation tasks, such as dialogue generation and story completion, require models to generate a coherent continuation given limited preceding context. The open-ended nature of these tasks brings new challenges to the neural auto-regressive text generators nowadays. Despite these neural models are good at producing human-like text, it is difficult for them to arrange causalities and relations between given facts and possible ensuing events. To bridge this gap, we propose a novel two-stage method which explicitly arranges the ensuing events in open-ended text generation. Our approach can be understood as a specially-trained coarse-to-fine algorithm, where an event transition planner provides a "coarse" plot skeleton and a text generator in the second stage refines the skeleton. Experiments on two open-ended text generation tasks demonstrate that our proposed method effectively improves the quality of the generated text, especially in coherence and diversity. The code is available at: \url{https://github.com/qtli/EventPlanforTextGen}.