LongStory: Coherent, Complete and Length Controlled Long story Generation
This addresses the challenge for writers and AI applications in creating structured long-form narratives, though it appears incremental as it builds on existing story generation methods.
The paper tackled the problem of generating long stories that are coherent, complete, and length-controlled, which current language models struggle with, and resulted in a model that outperforms baselines like Plotmachine in coherence, completeness, relevance, and repetitiveness.
A human author can write any length of story without losing coherence. Also, they always bring the story to a proper ending, an ability that current language models lack. In this work, we present the LongStory for coherent, complete, and length-controlled long story generation. LongStory introduces two novel methodologies: (1) the long and short-term contexts weight calibrator (CWC) and (2) long story structural positions (LSP). The CWC adjusts weights for long-term context Memory and short-term context Cheating, acknowledging their distinct roles. The LSP employs discourse tokens to convey the structural positions of a long story. Trained on three datasets with varied average story lengths, LongStory outperforms other baselines, including the strong story generator Plotmachine, in coherence, completeness, relevance, and repetitiveness. We also perform zero-shot tests on each dataset to assess the model's ability to predict outcomes beyond its training data and validate our methodology by comparing its performance with variants of our model.