CRIPAC-DIG/TextING
[ACL 2020] Tensorflow implementation for "Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks"
This project helps researchers and data scientists categorize documents based on their content. You provide a collection of text documents and their corresponding categories, and it outputs a model that can automatically assign new, unseen documents to the correct categories. It's ideal for NLP practitioners and researchers who need to classify various types of text data.
181 stars. No commits in the last 6 months.
Use this if you need to classify documents into predefined categories and want to leverage graph neural networks for improved accuracy, especially with new or infrequent words.
Not ideal if you need a quick, out-of-the-box solution without any programming or machine learning setup, or if your primary goal is topic modeling rather than classification.
Stars
181
Forks
57
Language
Python
License
—
Category
Last pushed
Apr 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/CRIPAC-DIG/TextING"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kyzhouhzau/NLPGNN
1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and...
IndexFziQ/GNN4NLP-Papers
A list of recent papers about Graph Neural Network methods applied in NLP areas.
qipeng/gcn-over-pruned-trees
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (authors' PyTorch...
kenqgu/Text-GCN
A PyTorch implementation of "Graph Convolutional Networks for Text Classification." (AAAI 2019)
daiquocnguyen/Graph-Transformer
Universal Graph Transformer Self-Attention Networks (TheWebConf WWW 2022) (Pytorch and Tensorflow)