Skip to content

janoschhaber/textstyletransfer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

UvA Language Style Transfer

This repo contains the code for Language Style Transfer project at the Univertsity of Amsterdam.

The code is based on the code that is originally developed for this paper: "Style Transfer from Non-Parallel Text by Cross-Alignment". Tianxiao Shen, Tao Lei, Regina Barzilay, and Tommi Jaakkola. arXiv:1705.09655

Data Format

Please name the corpora of two styles by "x.0" and "x.1" respectively, and use "x" to refer to them in options. Each file should consist of one sentence per line with tokens separated by a space.

The data/yelp/ directory contains an example Yelp review dataset.


Quick Start

To train a model, first create a tmp/ folder, then go to the code/ folder and run the following command:

python style_transfer.py --train ../data/yelp/sentiment.train --dev ../data/yelp/sentiment.dev --output ../tmp/sentiment.dev --vocab ../tmp/yelp.vocab --model ../tmp/model

To test the model, run the following command:

python style_transfer.py --test ../data/yelp/sentiment.test --output ../tmp/sentiment.test --vocab ../tmp/yelp.vocab --model ../tmp/model --load_model true

The model and results will be saved in the tmp/ folder.

Check code/options.py for all running options.


About

Repository of our writing style transfer project

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages