python - SpaCy TextCategorizer 管道详细信息

Question

我目前正在从事 NLP 项目。实际上，当我研究如何处理 NLP 时，我发现了一些关于 SpaCy 的文章。但是，因为我还是 python 新手，所以我不明白 SpaCy TextCategorizer Pipeline 是如何工作的。

有关于这个管道如何工作的详细信息吗？ TextCategorizer Pipeline 是否也使用文本特征提取，例如 Bag of Words、TF-IDF、Word2Vec 或其他？ SpaCy TextCategorizer 使用什么模型架构？有人可以帮我解释一下吗？

Answer 1

文档中有很多信息:

• https://spacy.io/usage/examples#textcat显示代码示例
• https://spacy.io/api/textcategorizer提供有关架构的详细信息:

The model supports classification with multiple, non-mutually exclusive labels. You can change the model architecture rather easily, but by default, the TextCategorizer class uses a convolutional neural network to assign position-sensitive vectors to each word in the document. The TextCategorizer uses its own CNN model, to avoid sharing weights with the other pipeline components. The document tensor is then summarized by concatenating max and mean pooling, and a multilayer perceptron is used to predict an output vector of length nr_class, before a logistic activation is applied elementwise. The value of each output neuron is the probability that some class is present.