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

[Nature Machine Intelligence' 21] "Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence"

Dieser Scanner findet Websites, die nicht direkt in Suchmaschinen auftauchen, aber trotzdem erreichbar sind.

Py-FEAT: Python Facial Expression Analysis Toolbox

Denoising Diffusion Probabilistic Models

[ICLR2021oral] Rethinking Architecture Selection in Differentiable NAS

WSDM2022 Challenge - Large scale temporal graph link prediction

An image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testingAn image base contains 490 images for learning (400 cars and 90 boats), and another 21 images for testing

Object DGCNN and DETR3D, Our implementations are built on top of MMdetection3D.

A collection of random and hastily hacked together scripts for investigating EU-DCC

Official PyTorch Implementation of paper "NeLF: Neural Light-transport Field for Single Portrait View Synthesis and Relighting", EGSR 2021.

CS50's Introduction to Artificial Intelligence Test Scripts

Code and datasets for the paper "KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction"

FedJAX is a library for developing custom Federated Learning (FL) algorithms in JAX.

This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.

Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"

Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL

Code for "Unsupervised State Representation Learning in Atari"

Whisper is a file-based time-series database format for Graphite.

Uses Open AI Gym environment to create autonomous cryptocurrency bot to trade cryptocurrencies.