TY - JOUR AU - Yao, Lili AU - Peng, Nanyun AU - Weischedel, Ralph AU - Knight, Kevin AU - Zhao, Dongyan AU - Yan, Rui PY - 2019/07/17 Y2 - 2024/03/28 TI - Plan-and-Write: Towards Better Automatic Storytelling JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 33 IS - 01 SE - AAAI Technical Track: Natural Language Processing DO - 10.1609/aaai.v33i01.33017378 UR - https://ojs.aaai.org/index.php/AAAI/article/view/4726 SP - 7378-7385 AB - <p>Automatic storytelling is challenging since it requires generating long, coherent natural language to describes a sensible sequence of events. Despite considerable efforts on automatic story generation in the past, prior work either is restricted in plot planning, or can only generate stories in a narrow domain. In this paper, we explore open-domain story generation that writes stories given a title (topic) as input. We propose a <em>plan-and-write</em> hierarchical generation framework that first plans a storyline, and then generates a story based on the storyline. We compare two planning strategies. The <em>dynamic</em> schema interweaves story planning and its surface realization in text, while the <em>static</em> schema plans out the entire storyline before generating stories. Experiments show that with explicit storyline planning, the generated stories are more diverse, coherent, and on topic than those generated without creating a full plan, according to both automatic and human evaluations.</p> ER -