训练 spacy 进行文本分类

Question

阅读文档并完成教程后，我想我会做一个小演示。原来我的模型不想训练。这是代码

import spacy
import random
import json

TRAINING_DATA = [
    ["My little kitty is so special", {"KAT": True}],
    ["Dude, Totally, Yeah, Video Games", {"KAT": False}],
    ["Should I pay $1,000 for the iPhone X?", {"KAT": False}],
    ["The iPhone 8 reviews are here", {"KAT": False}],
    ["Noa is a great cat name.", {"KAT": True}],
    ["We got a new kitten!", {"KAT": True}]
]

nlp = spacy.blank("en")
category = nlp.create_pipe("textcat")
nlp.add_pipe(category)
category.add_label("KAT")

# Start the training
nlp.begin_training()

# Loop for 10 iterations
for itn in range(100):
    # Shuffle the training data
    random.shuffle(TRAINING_DATA)
    losses = {}

    # Batch the examples and iterate over them
    for batch in spacy.util.minibatch(TRAINING_DATA, size=2):
        texts = [text for text, entities in batch]
        annotations = [{"textcat": [entities]} for text, entities in batch]
        nlp.update(texts, annotations, losses=losses)
    if itn % 20 == 0:
        print(losses)

当我运行它时，输出表明学到的很少。

{'textcat': 0.0}
{'textcat': 0.0}
{'textcat': 0.0}
{'textcat': 0.0}
{'textcat': 0.0}

这感觉不对。应该有错误或有意义的标签。预测证实了这一点。

import spacy
import random
import json

TRAINING_DATA = [
    ["My little kitty is so special", {"KAT": True}],
    ["Dude, Totally, Yeah, Video Games", {"KAT": False}],
    ["Should I pay $1,000 for the iPhone X?", {"KAT": False}],
    ["The iPhone 8 reviews are here", {"KAT": False}],
    ["Noa is a great cat name.", {"KAT": True}],
    ["We got a new kitten!", {"KAT": True}]
]

nlp = spacy.blank("en")
category = nlp.create_pipe("textcat")
nlp.add_pipe(category)
category.add_label("KAT")

# Start the training
nlp.begin_training()

# Loop for 10 iterations
for itn in range(100):
    # Shuffle the training data
    random.shuffle(TRAINING_DATA)
    losses = {}

    # Batch the examples and iterate over them
    for batch in spacy.util.minibatch(TRAINING_DATA, size=2):
        texts = [text for text, entities in batch]
        annotations = [{"textcat": [entities]} for text, entities in batch]
        nlp.update(texts, annotations, losses=losses)
    if itn % 20 == 0:
        print(losses)

感觉我的代码丢失了一些东西，但我不知道是什么。

Answer 1

如果您更新并使用 spaCy 3 - 上面的代码将不再有效。解决方案是进行一些更改进行迁移。我相应地修改了cantdutchthis中的示例。

变更摘要：

• 使用配置来更改架构。旧的默认值是“词袋”，新的默认值是使用注意力的“文本集成”。调整模型时请记住这一点
• 标签现在需要进行 one-hot 编码
• 界面add_pipe略有变化
• nlp.update现在需要一个Example对象而不是元组text，annotation

import spacy
# Add imports for example, as well as textcat config...
from spacy.training import Example
from spacy.pipeline.textcat import single_label_bow_config, single_label_default_config
from thinc.api import Config
import random

# labels should be one-hot encoded
TRAINING_DATA = [
    ["My little kitty is so special", {"KAT0": True}],
    ["Dude, Totally, Yeah, Video Games", {"KAT1": True}],
    ["Should I pay $1,000 for the iPhone X?", {"KAT1": True}],
    ["The iPhone 8 reviews are here", {"KAT1": True}],
    ["Noa is a great cat name.", {"KAT0": True}],
    ["We got a new kitten!", {"KAT0": True}]
]


# bow
# config = Config().from_str(single_label_bow_config)

# textensemble with attention
config = Config().from_str(single_label_default_config)

nlp = spacy.blank("en")
# now uses `add_pipe` instead
category = nlp.add_pipe("textcat", last=True, config=config)
category.add_label("KAT0")
category.add_label("KAT1")


# Start the training
nlp.begin_training()

# Loop for 10 iterations
for itn in range(100):
    # Shuffle the training data
    random.shuffle(TRAINING_DATA)
    losses = {}

    # Batch the examples and iterate over them
    for batch in spacy.util.minibatch(TRAINING_DATA, size=4):
        texts = [nlp.make_doc(text) for text, entities in batch]
        annotations = [{"cats": entities} for text, entities in batch]

        # uses an example object rather than text/annotation tuple
        examples = [Example.from_dict(doc, annotation) for doc, annotation in zip(
            texts, annotations
        )]
        nlp.update(examples, losses=losses)
    if itn % 20 == 0:
        print(losses)

Answer 2

根据 Ines 的评论，这就是答案。

import spacy
import random
import json

TRAINING_DATA = [
    ["My little kitty is so special", {"KAT": True}],
    ["Dude, Totally, Yeah, Video Games", {"KAT": False}],
    ["Should I pay $1,000 for the iPhone X?", {"KAT": False}],
    ["The iPhone 8 reviews are here", {"KAT": False}],
    ["Noa is a great cat name.", {"KAT": True}],
    ["We got a new kitten!", {"KAT": True}]
]

nlp = spacy.blank("en")
category = nlp.create_pipe("textcat")
category.add_label("KAT")
nlp.add_pipe(category)

# Start the training
nlp.begin_training()

# Loop for 10 iterations
for itn in range(100):
    # Shuffle the training data
    random.shuffle(TRAINING_DATA)
    losses = {}

    # Batch the examples and iterate over them
    for batch in spacy.util.minibatch(TRAINING_DATA, size=1):
        texts = [nlp(text) for text, entities in batch]
        annotations = [{"cats": entities} for text, entities in batch]
        nlp.update(texts, annotations, losses=losses)
    if itn % 20 == 0:
        print(losses)