# Custom POS tags with SpaCy for NER

Quite new to NLP and especially NER. I'm trying to train a NER model on a custom dataset. This is a dataset of houses for sale. As part of the entities I'm training the model to extract are reference numbers. These are of variable length (but usually between 4-9) and look like G55L7 or LPP01Z1-32.

How can I give these entities a new "POS tag", as from what I'm aware of, I can't find any in SpaCy's default list that would match these?

Ideally, I'd like to train this alongside a pre-existing NER model so that I can also extract ORGs which SpaCy already has support for.

For your first question, I would try to use Regex to identify the reference numbers since they seem unique comparing to normal words. I assume they are:

• All capital
• Start with one or more letters
• After follow numbers
• Any other pattern may follow (i.e. letters, numbers, hyphens)
• Do not include spaces

Could be something like this: \b[A-Z]+\d+([A-Z]|\d|-)*\b

I can imagine you could do it better...

Apart from the above answer, what you can do is create your own rule based entity matcher - https://spacy.io/usage/rule-based-matching

POS(part of speech) tagging won't help here.