search

TeangaNLP / teanga2

Teanga a dó
Apache License 2.0
0 stars 0 forks source link

Automatically build classifiers for corpora #10

Open jmccrae opened 6 months ago

jmccrae commented 6 months ago

This should probably be based on HuggingFace or similar tools

ml_system = teanga.huggingface.Model()
classifier = ml_system.token_classifier(corpus, "words", "pos")
classifier.predict({"text": "this is an example"})

We should support token, span, sentence and document classification.