XufengXufengXufeng/try_gcn

try different opts on word context graph with GCN and GAT to obtain word embeddings.

13
/ 100
Experimental

This project helps natural language processing practitioners explore different ways to create numerical representations (embeddings) of words. It takes your word context data and applies graph neural networks to generate word embeddings. This is for researchers or engineers working on tasks like text analysis or information retrieval who want to experiment with advanced embedding techniques.

No commits in the last 6 months.

Use this if you are interested in comparing how Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) perform against traditional methods like Node2Vec for generating word embeddings from context graphs.

Not ideal if you are looking for an out-of-the-box, production-ready solution for standard word embedding generation, as this project is more for experimental comparison.

natural-language-processing word-embeddings text-analysis machine-learning-research computational-linguistics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Jupyter Notebook

License

Last pushed

Mar 26, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/XufengXufengXufeng/try_gcn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.