Skip to content

Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events

Notifications You must be signed in to change notification settings

sofiadipace/O2S

 
 

Repository files navigation

Outline2Story

This repository contains source code for paper Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events:

@article{fang2021outline,
  title={Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events},
  author={Fang, Le and Zeng, Tao and Liu, Chaochun and Bo, Liefeng and Dong, Wen and Chen, Changyou},
  journal={arXiv preprint arXiv:2101.00822},
  year={2021}
}
  1. get source data (WritingPrompts, WikiPlots).
  2. data pre-processing (data/utils.py) -> need the bert_serving client running in order to compute the preprocessing.
  3. dataset statistics (dataset_statistics.py)
  4. training (choose from several different implementations on parallelism: train.py, train_apex.py, train_dist.py, train_dist_apex.py).
  5. generation, evaluation and analysis (generate.py, eval_ppl.py, generate_event_analysis.py).

Contact Le Fang: [email protected]

my email: [email protected]

Update on 2022: If you encounter package version issue, sorry for that I don't have a requirements.txt with exact versions. I used this package: https://github.com/nvidia/apex How to install apex from their Github Repo:

git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir ./

About

Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%