search

stanfordnlp / stanza

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
https://stanfordnlp.github.io/stanza/
Other
7.14k stars 880 forks source link

[QUESTION] : Named Entity Recognition (NER) on lemmatas / lemmatized words #1376

Closed sambaPython24 closed 2 months ago

sambaPython24 commented 3 months ago

Hey, thank you for your outstanding work.

After having read both the documentation on Named Entity Recognition and Lemmatization, I was wondering wether you could do Named Entity Recognition on the lemmatized words.

As an alternative, is that possible with the Client Regex Usage ? Thank you

AngledLuffa commented 3 months ago

We don't have a mechanism built in to do that, but you can certainly try passing the lemmas instead of the tokens. You would just need to copy the mechanism in ner_processor.py