Implementations of the models in the paper "Deconvolutional Paragraph Representation Learning" by Yizhe Zhang, Dinghan Shen, Guoyin Wang, Zhe Gan, Ricardo Henao and Lawrence Carin, NIPS 2017
- Tensorflow (version >1.0)
- CUDA, cudnn
- Run: python demo.py
- Options: options can be made by changing
option
class in the demo.py code.
opt.n_hidden
: number of hidden units.opt.layer
: number of CNN/DCNN layer [2,3,4].opt.lr
: learning rate.opt.batch_size
: number of batchsize.
- Training roughly takes 6-7 hours (around 10 epochs) to converge on a K80 GPU machine.
- See
output.txt
for a sample of screen output.
- download from data
For any question or suggestions, feel free to contact yz196@duke.edu
- Arxiv link: https://arxiv.org/abs/1708.04729
@inproceedings{zhang2017deconvolutional,
title={Deconvolutional Paragraph Representation Learning},
author={Zhang, Yizhe and Shen, Dinghan and Wang, Guoyin and Gan, Zhe and Henao, Ricardo and Carin, Lawrence},
Booktitle={NIPS},
year={2017}
}