Unsupervised Neural Text Simplification
This is the original implementation of the Unsupervised Neural Text Simplification system and their semi-supervised variants mentioned in the ACL 2019 long paper:
Sai Surya, Abhijit Mishra, Anirban Laha, Parag Jain, and Karthik Sankaranarayanan. Unsupervised Neural Text Simplification arXiv preprint arXiv:1810.07931 (2018).
Download tsdata.zip
from link and extract
unzip tsdata.zip
tsdata.zip
has
Train the models using
bash train.sh
train.sh
has
For more details and additional options, run the above scripts with the --help
flag.
Alternatively, visit the ipynb in google colaboratory to reproduce the results. To access pretrained models visit link. The folder predictions
has the generations from the pretrained models.
Note: Pretrained models were trained with pytorch 0.3.1.
bash translate.sh
translate.sh
is used for
Our code uses functions from https://github.com/artetxem/undreamt and https://github.com/senisioi/NeuralTextSimplification extensively.
If you use our system for academic research, please cite the following paper:
@inproceedings{surya-etal-2019-unsupervised,
title = "Unsupervised Neural Text Simplification",
author = "Surya, Sai and
Mishra, Abhijit and
Laha, Anirban and
Jain, Parag and
Sankaranarayanan, Karthik",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/P19-1198",
doi = "10.18653/v1/P19-1198",
pages = "2058--2068"
}