No description, website, or topics provided.
Matlab HTML
Switch branches/tags
Nothing to show
Clone or download
Jiwei li
Jiwei li assdf
Latest commit 2cea5c0 Sep 30, 2015
Permalink
Failed to load latest commit information.
Standard_LSTM change Sep 11, 2015
hier_LSTM change Sep 11, 2015
hier_LSTM_Attention assdf Sep 30, 2015
misc standard Jun 7, 2015
README.md asfsa Jun 20, 2015
a.txt asdf Sep 25, 2015
index.html asdf Sep 25, 2015

README.md

A Hierarchical Neural Autoencoder for Paragraphs and Documents

Implementations of the three models presented in the paper "A Hierarchical Neural Autoencoder for Paragraphs and Documents" by Jiwei Li, Minh-Thang Luong and Dan Jurafsky, ACL 2015

Requirements:

GPU

matlab >= 2014b

memory >= 4GB

Folders

Standard_LSTM: Standard LSTM Autoencoder

hier_LSTM: Hierarchical LSTM Autoencoder

hier_LSTM_Attention: Hierarchical LSTM Autoencoder with Attention

DownLoad Data

  • dictionary: vocabulary
  • train_permute.txt: training data for standard Model. Each line corresponds to one document/paragraph
  • train_source_permute_segment.txt: source training data for hierarchical Models. Each line corresponds to one sentence. An empty line starts a new document/sentence. Documents are reversed.
  • test_source_permute_segment.txt: target training data for hierarchical Model.

Training roughly takes 2-3 weeks for standard models and 4-6 weeks for hierarchical models on a K40 GPU machine.

For any question or bug with the code, feel free to contact jiweil@stanford.edu

@article{li2015hierarchical,
    title={A Hierarchical Neural Autoencoder for Paragraphs and Documents},
    author={Li, Jiwei and Luong, Minh-Thang and Jurafsky, Dan},
    journal={arXiv preprint arXiv:1506.01057},
    year={2015}
}