Neural language model-based approaches to automated story generation suffer from two important limitations. First, language model-based story generators generally do not work toward a given goal or ending. Second, they often lose coherence as the story gets longer. We propose a novel approach to automated story generation that treats the problem as one of generative question-answering. Our proposed story generation system starts with sentences encapsulating the final event of the story. The system then iteratively (1) analyzes the text describing the most recent event, (2) generates a question about "why" a character is doing the thing they are doing in the event, and then (3) attempts to generate another, preceding event that answers this question.
@article{arxiv.2112.03808,
title = {Automated Story Generation as Question-Answering},
author = {Louis Castricato and Spencer Frazier and Jonathan Balloch and Nitya Tarakad and Mark Riedl},
journal= {arXiv preprint arXiv:2112.03808},
year = {2021}
}