A Survey of Deep Learning Applied to Story Generation

Hou, Chenglong; Zhou, Chensong; Zhou, Kun; Sun, Jinan; Xuanyuan, Sisi

doi:10.1007/978-3-030-34139-8_1

Cited by 31 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They apply two types of generation control: 1) ending valence control (happy or sad ending), 2) storyline keywords. Hou et al [2019] categorized probabilistic story generation models into three categories: Theme-Oriented Models, Storyline-Oriented Models, and Human-Machine Interaction-Oriented Models. These models are different with respect to the user constraint, that is, the context given by a user to guide the generation probability of words.…”

Section: Research On Story Generationmentioning

confidence: 99%

Computational Storytelling and Emotions: A Survey

Mori¹,

Yamane²,

Mukuta³

et al. 2022

Preprint

View full text Add to dashboard Cite

Storytelling has always been vital for human nature. From ancient times, humans have used stories for several objectives including entertainment, advertisement, and education. Various analyses have been conducted by researchers and creators to determine the way of producing good stories. The deep relationship between stories and emotions is a prime example. With the advancement in deep learning technology, computers are expected to understand and generate stories. This survey paper is intended to summarize and further contribute to the development of research being conducted on the relationship between stories and emotions. We believe creativity research is not to replace humans with computers, but to find a way of collaboration between humans and computers to enhance the creativity. With the intention of creating a new intersection between computational storytelling research and human creative writing, we introduced creative techniques used by professional storytellers.

show abstract

Section: Research On Story Generationmentioning

confidence: 99%

Computational Storytelling and Emotions: A Survey

Mori¹,

Yamane²,

Mukuta³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For example, (Kybartas and Bidarra, 2017) summarizes progress in the areas of plot and space generation without much discussion around neural language models. (Hou et al, 2019) examine different deep learning models used in story generation and categorize them by their goals. However, there is still motivation to organize a survey in a different manner.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the Third Workshop on Narrative Understanding

2021

View full text Add to dashboard Cite

While natural language understanding of longform documents remains an open challenge, such documents often contain structural information that can inform the design of models encoding them. Movie scripts are an example of such richly structured text -scripts are segmented into scenes, which decompose into dialogue and descriptive components. In this work, we propose a neural architecture to encode this structure, which performs robustly on two multi-label tag classification tasks without using handcrafted features. We add a layer of insight by augmenting the encoder with an unsupervised 'interpretability' module, which can be used to extract and visualize narrative trajectories. Though this work specifically tackles screenplays, we discuss how the underlying approach can be generalized to a range of structured documents.

show abstract

“…Maintaining long-term narrative flow and consistency are important concerns when aiming to generate a plausible story (Porteous and Cavazza, 2009;Hou et al, 2019). Prior work on narrative text generation has focused on generating consistent stories via story outlines using keywords or key phrases (Xu et al, 2018;Yao et al, 2019), event-based representations (Riedl and Young, 2010;Fan et al, 2019), plot graphs (Li et al, Figure 1: Our aim is to generate a story given a title.…”

Section: Introductionmentioning

confidence: 99%

Narrative Text Generation with a Latent Discrete Plan

Jhamtani

Berg-Kirkpatrick

2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

Past work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first tag training stories with the desired type of plan, and then train generation models in a supervised fashion. In this paper, we propose a deep latent variable model that first samples a sequence of anchor words, one per sentence in the story, as part of its generative process. During training, our model treats the sequence of anchor words as a latent variable and attempts to induce anchoring sequences that help guide generation in an unsupervised fashion. We conduct experiments with several types of sentence decoder distributions -left-to-right and non-monotonic, with different degrees of restriction. Further, since we use amortized variational inference to train our model, we introduce two corresponding types of inference network for predicting the posterior on anchor words. We conduct human evaluations which demonstrate that the stories produced by our model are rated better in comparison with baselines which do not consider story plans, and are similar or better in quality relative to baselines which use external supervision for plans. Additionally, the proposed model gets favorable scores when evaluated on perplexity, diversity, and control of story via discrete plan.

show abstract

A Survey of Deep Learning Applied to Story Generation

Cited by 31 publications

References 26 publications

Computational Storytelling and Emotions: A Survey

Computational Storytelling and Emotions: A Survey

Proceedings of the Third Workshop on Narrative Understanding

Narrative Text Generation with a Latent Discrete Plan

Contact Info

Product

Resources

About