Story Generation

66 papers with code • 5 benchmarks • 5 datasets

Story generation is the task of automatically generating a coherent narrative, often from a set of premises or a brief summary.

Most implemented papers

Hierarchical Neural Story Generation

pytorch/fairseq ACL 2018

We explore story generation: creative systems that can build coherent and fluent passages of text about a topic.

A Temporal Variational Model for Story Generation

dwlmt/knowledgeable-stories 14 Sep 2021

Recent language models can generate interesting and grammatically correct text in story generation but often lack plot development and long-term coherence.

GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation

tkim-snu/GLACNet 28 May 2018

The task of multi-image cued story generation, such as visual storytelling dataset (VIST) challenge, is to compose multiple coherent sentences from a given sequence of images.

Plan-And-Write: Towards Better Automatic Storytelling

VioletPeng/language-model 14 Nov 2018

Automatic storytelling is challenging since it requires generating long, coherent natural language to describes a sensible sequence of events.

PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking

hrashkin/plotmachines EMNLP 2020

We propose the task of outline-conditioned story generation: given an outline as a set of phrases that describe key characters and events to appear in a story, the task is to generate a coherent narrative that is consistent with the provided outline.

On Faithfulness and Factuality in Abstractive Summarization

google-research-datasets/xsum_hallucination_annotations ACL 2020

It is well known that the standard likelihood training and approximate decoding objectives in neural text generation models lead to less human-like responses for open-ended tasks such as language modeling and story generation.

Transformer-based Conditional Variational Autoencoder for Controllable Story Generation

fangleai/TransformerCVAE 4 Jan 2021

In this paper, we advocate to revive latent variable modeling, essentially the power of representation learning, in the era of Transformers to enhance controllability without hurting state-of-the-art generation effectiveness.

Locally Typical Sampling

cimeister/typical-sampling 1 Feb 2022

Automatic and human evaluations show that, in comparison to nucleus and top-k sampling, locally typical sampling offers competitive performance (in both abstractive summarization and story generation) in terms of quality while consistently reducing degenerate repetitions.

Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation

dig-team/hanna-benchmark-asg COLING 2022

However, there is no consensus on which human evaluation criteria to use, and no analysis of how well automatic criteria correlate with them.

Event Representations for Automated Story Generation with Deep Neural Nets

lara-martin/ASTER 5 Jun 2017

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).