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 the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models

Attack on Confidence Estimation algorithm from the paper "Disrupting Deep Uncertainty Estimation Without Harming Accuracy"

RoMA: Robust Model Adaptation for Offline Model-based Optimization

LightSeq is a high performance training and inference library for sequence processing and generation implemented in CUDA

Code for the paper "How Attentive are Graph Attention Networks?"

Real life contra a deep learning project built using mediapipe and openc

System Combination for Grammatical Error Correction Based on Integer Programming

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

PyTorch implementation of Decoupling Value and Policy for Generalization in Reinforcement Learning

Trajectory Prediction with Graph-based Dual-scale Context Fusion

Image Captioning using CNN and Transformers

🏆 The 1st Place Submission to AICity Challenge 2021 Natural Language-Based Vehicle Retrieval Track (Alibaba-UTS submission)

Reinforcement Learning with Q-Learning Algorithm on gym's frozen lake environment implemented in python

SCU OlympicsRunning Baseline

Code for Learning Manifold Patch-Based Representations of Man-Made Shapes, in ICLR 2021.

iris - Open Source Photos Platform Powered by PyTorch

NeurIPS 2021 paper 'Representation Learning on Spatial Networks' code

Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

Multi-Person Extreme Motion Prediction