Hierarchical Attentional Hybrid Neural Networks for Document Classification

Jader Abreu, Luis Fred, David Macêdo, Cleber Zanchettin
1/20/2019
cs.CLcs.AIcs.LG

Official code: luisfredgs/cnn-hierarchical-network-for-document-classification (59 stars, last commit 2021-07-25).

Abstract

Document classification is a challenging task with important applications. The deep learning approaches to the problem have gained much attention recently. Despite the progress, the proposed models do not incorporate the knowledge of the document structure in the architecture efficiently and not take into account the contexting importance of words and sentences. In this paper, we propose a new approach based on a combination of convolutional neural networks, gated recurrent units, and attention mechanisms for document classification tasks. The main contribution of this work is the use of convolution layers to extract more meaningful, generalizable and abstract features by the hierarchical representation. The proposed method in this paper improves the results of the current attention-based approaches for document classification.

View on arXivView PDF

Code Implementations(1)

luisfredgs/cnn-hierarchical-network-for-document-classificationOfficial100%

This repository contains the implementation of paper "Hierarchical Attentional Hybrid Neural Networks for Document Classification"

5917Jupyter NotebookDec 10, 20185 years ago

Similar Papers

HDLTex: Hierarchical Deep Learning for Text Classification

86% match1 repo2772017

EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification

81% match2023

SECNN: Squeeze-and-Excitation Convolutional Neural Network for Sentence Classification

81% match2023

Graph Convolutional Networks for Text Classification

80% match1 repo1.4k2018

Text Classification: A Perspective of Deep Learning Methods

80% match2023

Feature Extraction Using Deep Generative Models for Bangla Text Classification on a New Comprehensive Dataset

80% match2023

Cite this paper

@article{abreu2019hierarchical,
  title  = {Hierarchical Attentional Hybrid Neural Networks for Document Classification},
  author = {Jader Abreu and Luis Fred and David Macêdo and Cleber Zanchettin},
  year   = {2019},
  eprint = {1901.06610},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1901.06610}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1901.06610.svg)](https://codeofpaper.com/paper/1901.06610)

Discussion