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

AI grand challenge 2020 Repo (Speech Recognition Track)

A lane detection integrated Real-time Instance Segmentation based on YOLACT (You Only Look At CoefficienTs)

Make your first PR. A beginner friendly repository made specifically for open source beginners. Add any program under any language (it can be anything from a simple program to a complex data structure algorithm). Happy coding...

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

This repository is to support contributions for tools for the Project CodeNet dataset hosted in DAX

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

PyTorch implementation for OCT-GAN Neural ODE-based Conditional Tabular GANs (WWW 2021)

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

NeuroGen: activation optimized image synthesis for discovery neuroscience

A Flow-based Generative Network for Speech Synthesis

Repo for the Tutorials of Day1-Day3 of the Nordic Probabilistic AI School 2021 (https://probabilistic.ai/)

Spectralformer: Rethinking hyperspectral image classification with transformers

OBBDetection: an oriented object detection toolbox modified from MMdetection

3rd place solution for the Weather4cast 2021 Stage 1 Challenge

[ECCVW2020] Robust Long-Term Object Tracking via Improved Discriminative Model Prediction (RLT-DiMP)

Unofficial implementation of HiFi-GAN+ from the paper "Bandwidth Extension is All You Need" by Su, et al.

[KDD 2021, Research Track] DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks

Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper. This code is for the part of the paper describing video-based avatars.

Official implementation of the paper 'High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network' in CVPR 2021

A wrapper around SageMaker ML Lineage Tracking extending ML Lineage to end-to-end ML lifecycles, including additional capabilities around Feature Store groups, queries, and other relevant artifacts.