README.md

Structured-Adversary

Code for our EMNLP 2019 paper titled 'Learning Rhyming Constraints using Structured Adversaries'

Link to EMNLP 2019 paper

Data

Data can be downloaded from the following link: Link to Data
DISCLAIMER: NOTE THAT THIS DATASET MAY CONTAIN WORDS THAT ARE ABUSIVE, OFFENSIVE, HURTFUL OR BIASED, OR MAY APPEAR OR BE CONSIDERED ABUSIVE, OFFENSIVE, HURTFUL WITH RESPECT TO AN INDIVIDUAL OR A COMMUNITY. THE AUTHORS DO NOT ENDORSE OR PROMOTE THE USE OF SUCH LANGUAGE OR WORDS, AND THESE HAVE PURELY BEEN INCLUDED AS A MATTER OF SCIENTIFIC ANALYSIS/INVESTIGATION.

Requirements

• python 3.6.7
• pytorch 0.4.1

Usage

• Download data from the above link to the main project directory
• Refer to code/Readme.md for instructions to run code

Reference

@article{jhamtani2019rhymgan,
  title={Learning Rhyming Constraints using Structured Adversaries},
  author={Harsh Jhamtani and Sanket Vaibhav Mehta and Jaime Carbonell and Taylor Berg-Kirkpatrick},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  month = {November},
  year = {2019}
}