Automated Story Generation as Question-Answering
This work addresses the challenge of generating coherent and goal-oriented stories for applications in creative writing and entertainment, representing an incremental improvement over existing methods.
The authors tackled the problem of automated story generation by addressing the lack of goal orientation and coherence in neural language models, proposing a method that treats story generation as generative question-answering, which improved coherence and goal-directedness in generated stories.
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.