如何为TextCategorizer培训创建黄金数据？

Question

我想用以下(text, label)对训练TextCategorizer模型.

标签颜色:

• 门是棕色的.
• 谷仓是红色的.
• 花是黄色的.

标签动物:

• 那匹马正在奔跑.
• 鱼正在跳跃.
• 鸡睡着了.

我正在复制TextCategorizer文档中的示例代码.

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

doc变量可能只是nlp("The door is brown.")等等.什么应该gold1和gold2？我猜他们应该是GoldParse对象,但我不知道你如何表示那些文本分类信息.

Answer 1

根据这个示例train_textcat.py,它应该类似于{'cats': {'ANIMAL': 0, 'COLOR': 1}}您想要训练多标签模型.此外,如果您只有两个类,则可以使用{'cats': {'ANIMAL': 1}}标签ANIMAL和{'cats': {'ANIMAL': 0}}标签COLOR.

您可以使用以下最小工作示例进行单类文本分类;

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)