Skip to content

MurathanKurfali/scene_segmentation

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

155 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Scene Segmentation through Sequential Sentence Classification

This repo has code for our paper "Breaking the Narrative: Scene Segmentation through Sequential Sentence Classification" that ranked 1st at the Shared Task on Scene Segmentation (STSS).

How to run

The easist way to run our model on your data is through Docker. Please put the novels you want segmented into the "data/test" directory following the shared task's JSON format.

Then you can simply build & run the docker image by simply running:

./build.sh
./run.sh

The built image will be ~9 GB and the predictions will be saved in "predictions" folder: One output file will be created per input file with the same name.

Citing

If you use the data or the model, please cite,

@inproceedings{kurfali2021breaking,
  title={Breaking the Narrative: Scene Segmentation through Sequential Sentence Classification},
  author={Kurfal{\i}, Murathan and Wir{\'e}n, Mats}
  journal={Shared Task on Scene Segmentation},
  year={2021}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 83.4%
  • Jsonnet 7.4%
  • Dockerfile 4.8%
  • Shell 4.4%