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

Meta Learning for Semi-Supervised Few-Shot Classification

MIRACLE (Missing data Imputation Refinement And Causal LEarning)

This repository contains various models targetting multimodal representation learning, multimodal fusion for downstream tasks such as multimodal sentiment analysis.

[CVPR2022] Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos

A hyperparameter optimization framework

Supporting code for the paper "Dangers of Bayesian Model Averaging under Covariate Shift"

Official implementation of "Robust channel-wise illumination estimation"

Official repository for "PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation"

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features

PyTorch implementation for 3D human pose estimation

Zalo AI challenge 2021 task hum to song

Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

Source code for the BMVC-2021 paper "SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation".

The official PyTorch code for NeurIPS 2021 ML4AD Paper, "Does Thermal data make the detection systems more reliable?"

The codebase for our paper "Generative Occupancy Fields for 3D Surface-Aware Image Synthesis" (NeurIPS 2021)

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Multi-Scale Aligned Distillation for Low-Resolution Detection (CVPR2021)

The story of Chicken for Club Bing

Implementation of CVPR 2020 Dual Super-Resolution Learning for Semantic Segmentation

Repository of 3D Object Detection with Pointformer (CVPR2021)