kaize0409/HyperGAT_TextClassification
Implementation of EMNLP2020 -- Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
This project helps data scientists and machine learning engineers categorize text documents into predefined topics or labels. It takes raw text data as input and produces classifications, even for documents that weren't part of the initial training. This is particularly useful for building robust text classification systems that can adapt to new data.
115 stars. No commits in the last 6 months.
Use this if you need to classify text documents and want a method that performs well even when encountering new, unseen documents after initial training.
Not ideal if you are looking for a system that can generate new categories on its own, as this project focuses on assigning texts to existing, known categories.
Stars
115
Forks
23
Language
Python
License
—
Category
Last pushed
Jan 09, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/kaize0409/HyperGAT_TextClassification"
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)