README.md

Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation

This repository provides code of the following paper:

Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation
Karin de Langis, Ryan Koo, Dongyeop Kang
EMNLP 2024 (main track, long paper)

Installation

The following command installs all necessary packages:

pip install -r requirements.txt

TBW

Citation

If you find this work useful for your research, please cite our papers:

@article{delangis2024dynamic,
  title={Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation},
  author={de Langis, Karin and Koo, Ryan and Kang, Dongyeop},
  journal={The Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2024}
}