Skip to content
PyTorch Implementation of Hierarchical Attention Network
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
HAN.ipynb
README.md
data_utils.py
grads.txt
imdb_data.py
models.py
train.py
utils.py

README.md

Hierarchical-Attention-Network

PyTorch implementation of Hierarchical Attention Network.

Modules

WordGRU: models.WordGRU

A GRU layer that takes in batches of words and encodes them

WordAttn: models.WordAttn

Attention Layer that takes in encoded words and generates Sentence Vectors

SentenceGRU: models.SentenceGRU

GRU layer that accepts documents as sentences and encodes the sentences

SentenceAttn: models.SentenceAttn

Attention Layer that takes in encoded sentences and generate document vectors

HAN: models.HAN

Monolithic class that takes in documents, and trains the network

Download and Prepare Data

Download the data from https://www.kaggle.com/utathya/imdb-review-dataset

Prepare the data for network using: python imdb_data.py imdb_master.csv

Training the network

python train.py

You can’t perform that action at this time.