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

Code for “ACE-HGNN: Adaptive Curvature ExplorationHyperbolic Graph Neural Network”

The dataset of tweets pulling from Twitters with keyword: Hydroxychloroquine, location: US, Time: 2020

The source code and data of the paper "Instance-wise Graph-based Framework for Multivariate Time Series Forecasting".

Do Smart Glasses Dream of Sentimental Visions? Deep Emotionship Analysis for Eyewear Devices

Image super-resolution through deep learning

Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021.

Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier

GrailQA: Strongly Generalizable Question Answering

The MLOps platform for innovators 🚀

Repository for training material for the 2022 SDSC HPC/CI User Training Course

Google AI Open Images - Object Detection Track: Open Solution

Code to reproduce the experiments in the paper "Transformer Based Multi-Source Domain Adaptation" (EMNLP 2020)

Flax is a neural network ecosystem for JAX that is designed for flexibility.

Saliency - Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).

System-oriented IR evaluations are limited to rather abstract understandings of real user behavior

Official implementation of deep Gaussian process (DGP)-based multi-speaker speech synthesis with PyTorch.

Official repository of the paper "GPR1200: A Benchmark for General-PurposeContent-Based Image Retrieval"

Content shared at DS-OX Meetup

This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.

Official PyTorch Implementation of Hypercorrelation Squeeze for Few-Shot Segmentation, arXiv 2021