Is there a way of training entity extraction models that I don't know about?

So I’m giving a lot of examples in the nlu.yml file. (ex: “Tell me aboutNeil Armstrong”). But for some reason it would not recognised entities that are not provided in the examples. I’m wondering why that is the case and how assistants like Google’s can recognise pretty much anything.

Hi @whenindan, from the example you provided it looks like you are trying to extract name entities. For name entities it is recommending you use the SpacyEntityExtractor in your NLU pipeline. The SpacyEntityExtractor is trained on a large corpus of data that will perform better at extracting names than manually tagging names in your training data.