kyzhouhzau/NLPGNN
1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and GraphSAGE based on message passing.
This project helps natural language processing (NLP) practitioners perform various text analysis tasks by combining advanced language models (like BERT or GPT2) with graph-based neural networks. You provide text data, and it outputs results for tasks like identifying specific entities in text, classifying the sentiment or topic of sentences, or even generating new text. It's designed for data scientists or NLP engineers who work with text-heavy applications.
337 stars. No commits in the last 6 months.
Use this if you need to build or experiment with state-of-the-art NLP models that combine transformer architectures with graph neural networks for tasks like named entity recognition or text classification.
Not ideal if you're looking for a simple, out-of-the-box solution without any programming or deep learning expertise.
Stars
337
Forks
66
Language
Python
License
MIT
Category
Last pushed
Aug 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/kyzhouhzau/NLPGNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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)
Cynwell/Text-Level-GNN
Text Level Graph Neural Network for Text Classification