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

Multi-scale discriminator feature-wise loss function

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving (ICCV 2021)

Readings for "A Unified View of Relational Deep Learning for Polypharmacy Side Effect, Combination Therapy, and Drug-Drug Interaction Prediction."

🌊 Online machine learning in Python

Zero-Cost Proxies for Lightweight NAS

NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Dataset

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Vision transformers (ViTs) have found only limited practical use in processing images

Visualizer using audio and semantic analysis to explore BigGAN (Brock et al., 2018) latent space.

Simple helper library to convert a collection of numpy data to tfrecord, and build a tensorflow dataset from the tfrecord.

Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

An OpenAI Gym environment for multi-agent car racing based on Gym's original car racing environment.

Car Parking Tracker Using OpenCv

Low-code/No-code approach for deep learning inference on devices

Code for ICMI2020 and ICMI2021 papers: "Studying Person-Specific Pointing and Gaze Behavior for Multimodal Referencing of Outside Objects from a Moving Vehicle" and "ML-PersRef: A Machine Learning-based Personalized Multimodal Fusion Approach for Referencing Outside Objects From a Moving Vehicle"

A Comparative Framework for Multimodal Recommender Systems

[内测中]前向式Python环境快捷封装工具，快速将Python打包为EXE并添加CUDA、NoAVX等支持。

My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control

[NeurIPS 2021] "Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems"

Atomistic Line Graph Neural Network