Pre-trained language models (PLMs) fail to generate long-form narrative text
because they do not consider global structure. As a result, the generated texts
are often incohesive, repetitive, or lack content. Recent work in story
generation reintroduced explicit content planning in the form of prompts,
keywords, or semantic frames. Trained on large parallel corpora, these models
can generate more logical event sequences and thus more contentful stories.
However, these intermediate representations are often not in natural language
and cannot be utilized by PLMs without fine-tuning. We propose generating story
plots using off-the-shelf PLMs while maintaining the benefit of content
planning to generate cohesive and contentful stories. Our proposed method,
ScratchPlot, first prompts a PLM to compose a content plan. Then, we generate
the story's body and ending conditioned on the content plan. Furthermore, we
take a generate-and-rank approach by using additional PLMs to rank the
generated (story, ending) pairs. We benchmark our method with various baselines
and achieved superior results in both human and automatic evaluation.

提出了一种新方法 ScratchPlot，使用 Pre-trained language models，利用 content planning 生成故事情节，并使用 generate-and-rank approach 对所生成的（story, ending）pairs 进行排序。实验表明，在人类评估和自动评估中都获得了更好的结果。