Controllable Neural Story Plot Generation via Reward Shaping
This addresses the issue of incoherent and uncontrolled story generation for users in creative writing or AI-assisted storytelling, representing an incremental improvement over existing language-modeling approaches.
The paper tackled the problem of generating coherent story plots with user-specified goals by introducing a reward-shaping technique that guides a pre-trained language model, resulting in automated evaluations showing consistent goal achievement and human studies indicating more plausible event ordering compared to baselines.
Language-modeling--based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to add to the story. LM techniques lack the ability to receive guidance from the user to achieve a specific goal, resulting in stories that don't have a clear sense of progression and lack coherence. We present a reward-shaping technique that analyzes a story corpus and produces intermediate rewards that are backpropagated into a pre-trained LM in order to guide the model towards a given goal. Automated evaluations show our technique can create a model that generates story plots which consistently achieve a specified goal. Human-subject studies show that the generated stories have more plausible event ordering than baseline plot generation techniques.