Plan-And-Write: Towards Better Automatic Storytelling

By Lili Yao, Nanyun Peng, Ralph M. Weischedel, Kevin Knight, Dongyan Zhao, Rui Yan. 2018

488 citations recorded by the source corpus.

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 plan-and-write hierarchical generation framework that first plans a storyline, and then generates a story based on the storyline. We compare two planning strategies. The dynamic schema interweaves story planning and its surface realization in text, while the static 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

The Woman Worked as a Babysitter: On Biases in Language Generation (2019, background): “…of NLG that are widely used in downstream tasks such as machine translation (Koehn, 2009), dialogue generation (Serban et al., 2016), and story generation (Yao et al., 2019); as such, biases propagated through the language models will have a profound impact on a variety of other NLG tasks.”
BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation (2021, background): “Natural language generation models are the central building blocks for many important artificial intelligence applications, including machine translation [17], text summarization [44], automatic storytelling [43], conversation bots [20], and writing assistants [39].”
Plug and Play Language Models: A Simple Approach to Controlled Text Generation (2019, neutral): “We explore controlled generation for assistive story writing (Peng et al., 2018; Luo et al., 2019; Yao et al., 2019; Fan et al., 2018).”
PEER: A Collaborative Language Model (2022, background): “The idea of having a separate planning stage has also been explored for other text generation tasks inlcuding summarization (Narayan et al., 2021), data-to-text generation (Moryossef et al., 2019) and story writing (Yao et al., 2019).”
CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning (2020, background): “Topical story generation (Fan et al., 2018; Yao et al., 2019) is also a related direction, while it targets generating longer, creative stories around the given topics, making it hard to directly adopt them to our task.”
ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning (2020, background): “, 2015, 2016, 2017), generating stories (Yao et al., 2019; Goldfarb-Tarrant et al., 2020), and forecasting social events (Li et al.”
Evaluation of Text Generation: A Survey (2020, methodology): “…Dong et al., 2019), using better sampling methods to reduce degeneration in decoding (Zellers et al., 2019; Holtzman et al., 2020), and learning to generate text with better discourse structures and narrative flow (Yao et al., 2018; Fan et al., 2019b; Dathathri et al., 2020; Rashkin et al., 2020).”
Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects (2019, methodology): “Prior knowledge could include story-lines in story generation (Yao et al., 2019), or historical responses in dialogue systems (We-ston et al., 2018).”
Enabling Language Models to Fill in the Blanks (2020, background): “Recent work seeks to generate stories given a title and storyline (Yao et al., 2019), entities (Clark et al., 2018), premise (Fan et al., 2018), or surrounding context and rare words (Ippolito et al., 2019).”
CTRLsum: Towards Generic Controllable Text Summarization (2020, background): “Wang et al. (2016), Mou et al. (2016), and Yao et al. (2019) use textual input to plan poetry, dialogue, and stories respectively.”
Progressive Generation of Long Text with Pretrained Language Models (2021, methodology): “Following (Yao et al., 2019), the keywords are extracted with the RAKE algorithm (Rose et al.”
Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning (2022, background): “These models, however, struggle with coherence and controllability across longer segments of text (Brown et al., 2020; Yao et al., 2019).”
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation (2020, background): “…outputs using a combination of simple automatic metrics not designed for long-form creative text generation (e.g., BLEU and ROUGE against a single reference) and crowdsourced ratings (McIntyre and Lapata, 2009; Yao et al., 2019; Fan et al., 2019) that preclude evaluating long-form narratives.”
InFillmore: Frame-Guided Language Generation with Bidirectional Context (2021, background): “…outline, existing approaches typically either model it as a latent variable, or use symbolic representations such as key phrases (Xu et al., 2018; Yao et al., 2019; Goldfarb-Tarrant et al., 2019; Gupta et al., 2019; Rashkin et al., 2020), short summaries (Jain et al., 2017; Chen et al., 2019),…”
Strategies for Structuring Story Generation (2019, methodology): “Several hierarchical models for story generation have recently been proposed (Xu et al., 2018; Yao et al., 2019), but it is not well understood which properties characterize a good decomposition.”
Text Editing by Command (2020, background): “…using storylines (Peng et al., 2018), events (Martin et al., 2017; Harrison et al., 2017), plot words or word skeletons (Xu et al., 2018; Ippolito et al., 2019), plans (Yao et al., 2019), story ending (Tambwekar et al., 2019), and outlines (Rashkin et al., 2020) as various forms of constraints.”
Content Planning for Neural Story Generation with Aristotelian Rescoring (2020, methodology): “Existing work in neural story generation has established the strength of adding a content planning stage to structure the generated content (Yao et al., 2019; Fan et al., 2019) (discussed in more detail in Section 7).”
Controllable Neural Story Plot Generation via Reward Shaping (2018, result): “Similar to our task, Fan et al. [2018] and Yao et al. [2019] focus on a form of controllability in which a theme, topic, or title is given.”
Collaborative Storytelling with Large-scale Neural Language Models (2020, background): “[Yao et al. 2019] approach the task by first generating a plot outline and then filling in the language.”