This repository contains an easy and intuitive approach to zero-shot and few-shot NER using internal spaCy embeddings.
Project description
Concise Concepts
When wanting to apply NER to concise concepts, it is really easy to come up with examples, but pretty difficult to train an entire pipeline. Concise Concepts uses word similarity based on few-shots to get you going with easy!
Install
pip install classy-classification
Quickstart
import spacy
import concise_concepts
data = {
"fruit": ["apple", "pear", "orange"],
"vegetable": ["broccoli", "spinach", "tomato"],
"meat": ["chicken", "beef", "pork", "fish", "lamb"]
}
text = """
Heat the oil in a large pan and add the Onion, celery and carrots.
Cook over a medium–low heat for 10 minutes, or until softened.
Add the courgette, garlic, red peppers and oregano and cook for 2–3 minutes.
Later, add some oranges and chickens. """
nlp = spacy.load('en_core_web_lg')
nlp.add_pipe("concise_concepts", config={"data": data})
doc = nlp(text)
print([(ent.text, ent.label_) for ent in doc.ents])
# Output:
#
# [('Onion', 'VEGETABLE'), ('Celery', 'VEGETABLE'), ('carrots', 'VEGETABLE'),
# ('garlic', 'VEGETABLE'), ('red peppers', 'VEGETABLE'), ('oranges', 'FRUIT'),
# ('chickens', 'MEAT')]
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
concise-concepts-0.1.0.tar.gz
(8.4 kB
view hashes)
Built Distribution
Close
Hashes for concise_concepts-0.1.0-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 544396da221b13a9100c463f66098c23cb660567d7cc33754010e5599c563324 |
|
| MD5 | 944b4b59130fb8e45032c77853832a55 |
|
| BLAKE2b-256 | 693fa7cd68175c504657aff71b7719f73632d5639aefba579b487a2f77c1267b |
