Code for "Jhamtani H.*, Gangal V.*, Hovy E. and Nyberg E. Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models" Workshop on Stylistic Variation, EMNLP 2017
Code for "Jhamtani H., Gangal V., Hovy E. and Nyberg E. Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models" Workshop on Stylistic Variation, EMNLP 2017
Link to paper: https://arxiv.org/abs/1707.01161
python mt_main.py preprocessing
python mt_main.py train 10 pointer_model
For inference:
python mt_main.py inference tmp/pointer_model7.ckpt greedy
There are two post-processing actions which one may be interested in performing:
python dictionary_baseline.py ../../data/shakespeare.dict ../../data/test.modern.nltktok ../../data/test.dictBaseline
perl multi-bleu.perl -lc ../../data/test.original.nltktok < ../../data/test.dictBaseline
If you use this code or the processed data, please consider citing our work:
@article{jhamtani2017shakespearizing,
title={Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models},
author={Jhamtani, Harsh and Gangal, Varun and Hovy, Eduard and Nyberg, Eric},
journal={EMNLP 2017},
volume={6},
pages={10},
year={2017}
}
Additionally, if you use the data, please consder citing "Wei Xu, Alan Ritter, William B Dolan, Ralph Grish- man, and Colin Cherry. 2012. Paraphrasing for style. In 24th International Conference on Computational Linguistics, COLING 2012."