Plot Writing From Pre-Trained Language Models
Yiping Jin, Vishakha Kadam, Dittaya Wanvarie
Abstract: 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 offthe-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 generateand-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.