Event Representations for Automated Story Generation with Deep Neural Nets

By Lara J. Martin, Prithviraj Ammanabrolu, William Hancock, Shruti Singh, Brent Harrison, Mark O. Riedl. 2017

231 citations recorded by the source corpus.

Automated story generation is the problem of automatically selecting a sequence of events, actions, or words that can be told as a story. We seek to develop a system that can generate stories by learning everything it needs to know from textual story corpora. To date, recurrent neural networks that learn language models at character, word, or sentence levels have had little success generating coherent stories. We explore the question of event representations that provide a mid-level of abstraction between words and sentences in order to retain the semantic information of the original data while minimizing event sparsity. We present a technique for preprocessing textual story data into event sequences. We then present a technique for automated story generation whereby we decompose the problem into the generation of successive events (event2event) and the generation of natural language sentences from events (event2sentence). We give empirical results comparing different event representations and their effects on event successor generation and the translation of events to natural language.

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

Hierarchical Neural Story Generation (2018, methodology): “Martin et al. (2017) decompose story generation into two steps, ﬁrst converting text into event representations, then modeling stories as sequences of events before translating back to natu-ral language.”
Plan-And-Write: Towards Better Automatic Storytelling (2018, background): “However, Martin et al. [2018] did not conduct experiments on full story generation.”
Towards Controllable Story Generation (2018, background): “Martin et al. (2017) train a recurrent encoder-decoder neural network (Sutskever et al., 2014) to predict the next event in the story.”
Evaluation of Text Generation: A Survey (2020, background): “, story generation (Fan et al., 2018; Martin et al., 2017) or long-form question answering (Fan et al.”
Planning with Learned Entity Prompts for Abstractive Summarization (2021, background): “In story generation, there has been some work on exploring events (Martin et al., 2018) or sequences of words (Yao et al.”
VScript: Controllable Script Generation with Visual Presentation (2022, unknown): “Martin et al. (2018) decompose a story as a sequence of events and apply sequence modelling to generate the story.”
Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks (2021, methodology): “For example, Martin et al. (2017) use a neural network to translate events into natural language.”
Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning (2022, methodology): “based—capable of producing stories (Roemmele, 2016; Khalifa et al., 2017; Martin et al., 2018; Clark et al., 2018; Fan et al., 2018; Ammanabrolu et al., 2021).”
A Long Way to Go: Investigating Length Correlations in RLHF (2023, unknown): “Finally, other past uses of RL in NLP (Ammanabrolu & Riedl, 2018; Martin et al., 2017; Ramamurthy et al., 2023) have largely faced different sets of issues due to reward not coming from models learned over human preferences.”
Text Editing by Command (2020, background): “…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., 2017; Harrison et al., 2017), plot words or word skeletons (Xu et al., 2018; Ippolito et al., 2019), plans (Yao et al., 2019), story…”
Strategies for Structuring Story Generation (2019, background): “Recent work extended this to modelling story events (Martin et al., 2017; Mostafazadeh et al., 2016), plot graphs (Li et al.”
Facts2Story: Controlling Text Generation by Key Facts (2020, background): “…neural techniques for story generation struggled with staying coherent for long periods of time, and proposed solutions in the form of two-stage processes which ﬁrst generate skeletal structures and then expand them into longer texts (Harrison et al., 2017; Martin et al., 2018; Yao et al., 2018).”
InFillmore: Frame-Guided Language Generation with Bidirectional Context (2021, background): “…(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), verb-argument tuples (Martin et al., 2018), or PropBank predicates and arguments (Fan et al., 2019; Goldfarb-Tarrant et al., 2020).”
Content Planning for Neural Story Generation with Aristotelian Rescoring (2020, background): “Martin et al. (2018) decompose the problem of story generation into generation of successive events”
Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learning (2021, methodology): “…conditioning on content-relevant features such as plot outlines (Fan et al., 2018; Peng et al., 2018; Rashkin et al., 2020) or by hierarchical reasoning with abstract representations that help constrain story progression (Martin et al., 2018; Yao et al., 2019; Fan et al., 2019; Peng et al., 2021).”
Controllable Neural Story Generation via Reinforcement Learning (2018, methodology): “The pre-trained model is identical to the “generalized multiple sequential event2event” model in Martin et al. (2018).”