a-PyTorch-Tutorial-to-Text-Classification and hierarchical-attention-networks

These two tools are competitors, offering implementations of Hierarchical Attention Networks for text classification in PyTorch and TensorFlow, respectively, requiring users to choose one based on their preferred deep learning framework.

Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 0/25
Adoption 9/25
Maturity 16/25
Community 20/25
Stars: 249
Forks: 54
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 87
Forks: 25
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About a-PyTorch-Tutorial-to-Text-Classification

sgrvinod/a-PyTorch-Tutorial-to-Text-Classification

Hierarchical Attention Networks | a PyTorch Tutorial to Text Classification

This is a tutorial for deep learning developers who want to build a model that can automatically label text documents with specific categories. You provide the text content, and the model classifies it into predefined categories, also highlighting the most important words and sentences that led to its decision. This is ideal for machine learning engineers and researchers working with natural language processing.

text-classification natural-language-processing deep-learning-implementation hierarchical-attention-networks PyTorch-development

About hierarchical-attention-networks

qtuantruong/hierarchical-attention-networks

TensorFlow implementation of the paper "Hierarchical Attention Networks for Document Classification"

This project helps you automatically categorize text documents like customer reviews or product feedback. You input a collection of text documents, and it outputs classifications, making it easier to sort and analyze large volumes of text. This is designed for data scientists or researchers who need to classify unstructured text efficiently.

document-classification text-analytics customer-feedback sentiment-analysis research-data-categorization

Scores updated daily from GitHub, PyPI, and npm data. How scores work