Towards Controllable Story Generation

By Nanyun Peng, Marjan Ghazvininejad, Jonathan May, Kevin Knight. 2018

147 citations recorded by the source corpus.

We present a general framework of analyzing existing story corpora to generate controllable and creative new stories. The proposed framework needs little manual annotation to achieve controllable story generation. It creates a new interface for humans to interact with computers to generate personalized stories. We apply the framework to build recurrent neural network (RNN)-based generation models to control story ending valence and storyline. Experiments show that our methods successfully achieve the control and enhance the coherence of stories through introducing storylines. with additional control factors, the generation model gets lower perplexity, and yields more coherent stories that are faithful to the control factors according to human evaluation.

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 Curious Case of Neural Text Degeneration (2019, background): “…includes conditional story generation and contextual text continuation (as in Figure 1), has recently become a promising research direction due to signiﬁcant advances in neural language models (Clark et al., 2018; Holtzman et al., 2018; Fan et al., 2018; Peng et al., 2018; Radford et al., 2019).”
Pretraining Language Models with Human Preferences (2023, background): “…2017; Fan et al., 2018; Keskar et al., 2019) has been shown to be successful across tasks as diverse as as controllable language generation (Peng et al., 2018; Dai et al., 2019), mitigating toxicity (Gehman et al., 2020; Xu et al., 2020; Lu et al., 2022) and robotic control (Chen et al.,…”
Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, methodology): “One solution is the use of controllable neural text generation methods, in particular conditional training (Fan, Grangier, and Auli, 2018; Kikuchi et al., 2016; Peng et al., 2018) and weighted decoding (Ghazvininejad et al., 2017; Baheti et al., 2018).”
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).”
Neural Text Generation with Unlikelihood Training (2019, background): “Some other lines of work of note are the use of generative control (Kikuchi et al., 2016; Fan et al., 2017; Peng et al., 2018; See et al., 2019) and the retrieve-and-reﬁne setting (Weston et al., 2018; Guu et al., 2018).”
What makes a good conversation? How controllable attributes affect human judgments (2019, methodology): “Given these constraints, we study two con-trol methods: conditional training (Fan et al., 2018; Kikuchi et al., 2016; Peng et al., 2018) and weighted decoding (Ghazvininejad et al., 2017).”
Plan-And-Write: Towards Better Automatic Storytelling (2018, background): “Some recent work explored story generation with additional information (Bowden et al. 2016; Peng et al. 2018; Guan, Wang, and Huang 2019).”
Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs (2021, background): “…end-to-end training with an additional trigger to control the attributes, such as sentiment (Shen et al., 2017; Hu et al., 2017; Fu et al., 2018; Peng et al., 2018; Dai et al., 2019), tense (Logeswaran et al., 2018), plots (Ammanabrolu et al., 2020; Fan et al., 2019; Tambwekar et al., 2019;…”
Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View (2021, background): “…template-like (Liu et al. 2017; Wiseman, Shieber, and Rush 2018; Shen et al. 2020; Li and Rush 2020; Ye et al. 2020) or controllable generation (Peng et al. 2018; Fan, Lewis, and Dauphin 2019; Shen et al. 2019; Parikh et al. 2020), which encourage the overlap between given structured data and…”
Controllable Neural Story Plot Generation via Reinforcement Learning (2018, background): “th a second model that translates abstract events into human-readable sentences. We borrow the event representation for our work and also replicate the sequenceto-sequence technique for our baseline. Peng et al. (2018) propose a means of controlling for the emotional valence of story endings with a ”
Text Editing by Command (2020, background): “As narratives are often aimed at particular goals expressed in terms of outlines and plans, much of the literature in Story Generation is framed as a form of controllable generation, using storylines (Peng et al., 2018), events (Martin et al.”
Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning (2022, background): “Story generation can be controlled by conditioning generation on high-level plot outlines (Fan et al., 2018; Peng et al., 2018; Rashkin et al., 2020), story in-ﬁlling (Don-ahue et al., 2020; Wang et al., 2020), ﬁne-tuning on goals (Tambwekar et al., 2019a; Alabdulkarim et al., 2021).”
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation (2020, background): “More recent work uses deep learning to generate stories by training neural models with limited context (Peng et al., 2018; Fan et al., 2018; Goldfarb-Tarrant et al., 2019) and structured knowledge, either external (Mao et al., 2019; Guan et al., 2020; Goldfarb-Tarrant et al., 2020) or derived (Yao…”
Learning to Control the Fine-grained Sentiment for Story Ending Generation (2019, methodology): “Recently, many approaches are proposed to generate a better story in terms of coherence (Jain et al., 2017; Xu et al., 2018), rationality (Li et al., 2018), topic-consistence (Yao et al., 2018a).”
Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning (2021, background): “One means of controlling story generation is to condition generation on high-level plot outlines (Fan et al., 2018; Peng et al., 2018; Rashkin et al., 2020) or”
A Survey of the Usages of Deep Learning for Natural Language Processing (2020, methodology): “[208], who used LSTMs to generate stories, providing an input to specify whether the”