Skip to content

dominikmartinez/fairseq_easy_extend_nlp2

 
 

Repository files navigation

How to reward non-autoregressive models: Minimum risk training with string-based metrics in NMT

This repository provides the implementation for the paper "How to reward non-autoregressive models: Minimum risk training with string-based metrics in NMT", which was written as part of the "Natural Language Processing 2" course at the University of Amsterdam.

Requirements

This repository is a simplified fairseq extension. For installation, please follow the instructions of fairseq.

Reproducibility

The experiments were executed using the fairseq.ipynb notebook. Feel free to reach out in case of any questions regarding reproducibility or implementation details.

About

implementation for UvA.NLP2.project1

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 94.4%
  • Jupyter Notebook 5.6%