d46a5baebee981f4505b022a8a139a62d3b2e1e3
This is a multi-class, multi-label network that categorises text into one of ~160 categories, mostly relating to the African continent.
The training dataset is a proprietry dataset, consisting of news articles that have been manually categorised.
The trained model is freely available, as is the training and evaluation code; the dataset is unfortunately not.
Description
A multi-class, multi-label NLP network that categorises text into one of ~160 categories, mostly relating to the African continent.
Languages
Python
99.4%
Makefile
0.6%