Nested named entity recognition

[stulcrad]

Hello,

I would love to train a model on a nested NER dataset, and I would like to ask if someone has any experience with how huggingface libraries interact with it and if it will even output the desired result. For example, if a person’s name “John Doe” is characterized as:
John Doe - P(person)
John - PF(person first name)
Doe - PS(person surname)
With BIO format John is B-P / B-PF and Doe I-P / B-PS.

[stulcrad]

If anyone reading this would be interested, I solved it using this discussion

Multi-label token classification

Hi! I am trying to solve a token classification problem in a multi-label setup. So far I haven’t found the best path to do it. Unlike AutoModelForSequenceClassification, AutoModelForTokenClassification lacks the problem_type parameter, where you can specify that you’re working with multi-label. Should I deepen into logits and create a custom loss or is there a more straightforward solution? Thanks!