TensorFlow implementation of the paper "Hierarchical Attention Networks for Document Classification"

Last update: Dec 05, 2022

Overview

Hierarchical Attention Networks for Document Classification

This is an implementation of the paper Hierarchical Attention Networks for Document Classification, NAACL 2016.

Requirements

Python 3
Tensorflow > 1.0
Pandas
Nltk
Tqdm
Glove pre-trained word embeddings

Data

We use the data provided by Tang et al. 2015, including 4 datasets:

IMDB
Yelp 2013
Yelp 2014
Yelp 2015

Note: The original data seems to have an issue with unzipping. I re-uploaded the data to GG Drive for better downloading speed. Please request for access permission.

Usage

First, download the datasets and unzip into data folder.
Then, run script to prepare the data (default is using Yelp-2015 dataset):

python data_prepare.py

Train and evaluate the model:
(make sure Glove embeddings are ready before training)

wget http://nlp.stanford.edu/data/glove.6B.zip
unzip glove.6B.zip

python train.py

Print training arguments:

python train.py --help

optional arguments:
  -h, --help            show this help message and exit
  --cell_dim            CELL_DIM
                        Hidden dimensions of GRU cells (default: 50)
  --att_dim             ATTENTION_DIM
                        Dimensionality of attention spaces (default: 100)
  --emb_dim             EMBEDDING_DIM
                        Dimensionality of word embedding (default: 200)
  --learning_rate       LEARNING_RATE
                        Learning rate (default: 0.0005)
  --max_grad_norm       MAX_GRAD_NORM
                        Maximum value of the global norm of the gradients for clipping (default: 5.0)
  --dropout_rate        DROPOUT_RATE
                        Probability of dropping neurons (default: 0.5)
  --num_classes         NUM_CLASSES
                        Number of classes (default: 5)
  --num_checkpoints     NUM_CHECKPOINTS
                        Number of checkpoints to store (default: 1)
  --num_epochs          NUM_EPOCHS
                        Number of training epochs (default: 20)
  --batch_size          BATCH_SIZE
                        Batch size (default: 64)
  --display_step        DISPLAY_STEP
                        Number of steps to display log into TensorBoard (default: 20)
  --allow_soft_placement ALLOW_SOFT_PLACEMENT
                        Allow device soft device placement

Results

With the Yelp-2015 dataset, after 5 epochs, we achieved:

69.79% accuracy on the dev set
69.62% accuracy on the test set

No systematic hyper-parameter tunning was performed. The result reported in the paper is 71.0% for the Yelp-2015.

TensorFlow implementation of the paper "Hierarchical Attention Networks for Document Classification"

Related tags

Overview

Hierarchical Attention Networks for Document Classification

Requirements

Data

Usage

Results

Owner

Quoc-Tuan Truong

img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation

Codes for building and training the neural network model described in Domain-informed neural networks for interaction localization within astroparticle experiments.

AbelNN: Deep Learning Python module from scratch

[ICCV2021] Learning to Track Objects from Unlabeled Videos

This is a code repository for paper OODformer: Out-Of-Distribution Detection Transformer

NeuralDiff: Segmenting 3D objects that move in egocentric videos

TensorFlow2 Classification Model Zoo playing with TensorFlow2 on the CIFAR-10 dataset.

NP DRAW paper released code

Code release for The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification (TIP 2020)

ZeroGen: Efficient Zero-shot Learning via Dataset Generation

[ICCV 2021] Code release for "Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks"

PyTorch code for EMNLP 2021 paper: Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System

Open AI's Python library

Fortuitous Forgetting in Connectionist Networks

An SE(3)-invariant autoencoder for generating the periodic structure of materials

The pure and clear PyTorch Distributed Training Framework.

VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning

Improving Generalization Bounds for VC Classes Using the Hypergeometric Tail Inversion

A Python package to process & model ChEMBL data.

Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving