Trouble training for Portuguese

[ines (Ines Montani)]

Yay, glad it works now!

@rogeriobromfman

When it suggested just part of a name, I accepted. When it suggested a name together with some extra words, I ignored. I didn’t want to reject, as the selected part did contain a name, but I didn’t want the model picking up more than the name…

Okay, this probably explains a lot! You should definitely reject incomplete entities and any other suggestions that are wrong (even if it's painful sometimes if the model almost got it right ). My comment on this thread explains the reasoning behind this in more detail:

How to score incompletely highlighted entities?

If you’re using an active learning-powered recipe, those entities are both examples of suggestions you should reject. By rejecting incorrect boundaries, you’re essentially telling the model “Nope, try again!”, moving it towards the correct boundaries. Each token can only be part of one entity, so if you accepted a partial match like “Hong”, the feedback the model would get from this is “Yep, in contexts like this, ‘Hong’ is a single-token GPE entity and wins over all other possible analyses cont…

So if you've been annotating differently, I'd definitely suggest to convert your existing annotations to gold-standard, pre-train your model from that and then try the binary workflow again starting with a fresh dataset. You could also try adding some patterns when you run ner.teach, to make sure the model sees enough positive examples during annotation. For example, some street names or abstract patterns of possible street names could work well (e.g. any token + - + any token + "avenue").

@rogeriobromfman

I think that one of the big problems I’ll have is that the streets in Brazil are usually named after people. So the model will have to learn to differentiate when a name is a person or a street. It will have to understand that the street names will usually start with the words “street” or “avenue”, and will typically be followed by a comma and a number. House numbers here are put after the street name.

This is interesting and definitely something I'd keep an eye on! (Also a nice example of why it's always super important to reason about the data and be familiar with both the language and the domain!)