How do I create gold data for TextCategorizer training?

问题

I want to train a TextCategorizer model with the following (text, label) pairs.

Label COLOR:

The door is brown.
The barn is red.
The flower is yellow.

Label ANIMAL:

The horse is running.
The fish is jumping.
The chicken is asleep.

I am copying the example code in the documentation for TextCategorizer.

textcat = TextCategorizer(nlp.vocab)
losses = {}
optimizer = nlp.begin_training()
textcat.update([doc1, doc2], [gold1, gold2], losses=losses, sgd=optimizer)

The doc variables will presumably be just nlp("The door is brown.") and so on. What should be in gold1 and gold2? I'm guessing they should be GoldParse objects, but I don't see how you represent text categorization information in those.

回答1:

According to this example train_textcat.py it should be something like {'cats': {'ANIMAL': 0, 'COLOR': 1}} if you want to train a multi-label model. Also, if you have only two classes, you can simply use {'cats': {'ANIMAL': 1}} for label ANIMAL and {'cats': {'ANIMAL': 0}} for label COLOR.

You can use the following minimal working example for a one category text classification;

import spacy

nlp = spacy.load('en')

train_data = [
    (u"That was very bad", {"cats": {"POSITIVE": 0}}),
    (u"it is so bad", {"cats": {"POSITIVE": 0}}),
    (u"so terrible", {"cats": {"POSITIVE": 0}}),
    (u"I like it", {"cats": {"POSITIVE": 1}}),
    (u"It is very good.", {"cats": {"POSITIVE": 1}}),
    (u"That was great!", {"cats": {"POSITIVE": 1}}),
]


textcat = nlp.create_pipe('textcat')
nlp.add_pipe(textcat, last=True)
textcat.add_label('POSITIVE')
optimizer = nlp.begin_training()
for itn in range(100):
    for doc, gold in train_data:
        nlp.update([doc], [gold], sgd=optimizer)

doc = nlp(u'It is good.')
print(doc.cats)

来源：https://stackoverflow.com/questions/48834832/how-do-i-create-gold-data-for-textcategorizer-training

标签

spacy