使用 Spacy 进行 NER 训练 [英] NER training using Spacy

问题描述

在空的 NER 模型上运行火车时，我应该只包含标记数据(必须包含至少一个实体的数据)，还是应该包含根本不包含任何标签的数据(在这种情况下，教学在某些情况下这些词没有任何标签的模型)?

When running a train on an empty NER model, should I include only labeled data (data that contain necessarily at least one entity), or should I also include data that do not contain any label at all (in this case, teaching the model that in some circunstances these words do not have any label)?

推荐答案

如果您查看 NER 的常用训练数据(您可以在 http://nlpprogress.com/english/named_entity_recognition.html )，您会看到大多数/每个示例都至少有一个实体.

If you look at the commonly used training data for NER (you can find links at http://nlpprogress.com/english/named_entity_recognition.html ), you’ll see that most/every example has at least one entity.

尽管如此，模型可能了解到大多数实体类型都不会出现在任何给定的示例中.但是你总是可以尝试添加真正否定的例子，看看是否有帮助

Despite that, the model probably learns that most entity types don’t show up in any given example. But you can always try adding examples of true negatives and see if that helps

这篇关于使用 Spacy 进行 NER 训练的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！