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

A list of Machine Learning Art Colabs

This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".

Deep-learning-roadmap - All You Need to Know About Deep Learning - A kick-starter

PyContinual (An Easy and Extendible Framework for Continual Learning)

A PyTorch implementation of the Relational Graph Convolutional Network (RGCN).

Single object tracking and segmentation.

《Towards High Fidelity Face Relighting with Realistic Shadows》(CVPR 2021)

Code and data for the EMNLP 2021 paper "Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts". Coming soon!

mlpack: a scalable C++ machine learning library --

Geometric Vector Perceptron --- a rotation-equivariant GNN for learning from biomolecular structure

Airborne Optical Sectioning (AOS) is a wide synthetic-aperture imaging technique

An OpenAI Gym environment for Super Mario Bros

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Python版OpenCVのTracking APIのサンプルです。DaSiamRPNアルゴリズムまで対応しています。

Source Code for DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances (https://arxiv.org/pdf/2012.01775.pdf)

Hunt down social media accounts by username across social networks

Speech recognition tool to convert audio to text transcripts, for Linux and Raspberry Pi.

GeneDisco is a benchmark suite for evaluating active learning algorithms for experimental design in drug discovery.

DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generative Transformers

Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.