nlp-uoregon/trankit

Training a model for pre-tagged data

Closed this issue · 1 comments

amir-zeldes commented

Hi and thanks for making this toolkit available!

I wanted to ask whether it's possible to train a model to predict morphology (FEATS) and/or lemmatization based on pre-tagged text (for example POS tags already in a CoNLL-U input file)?

Bachstelze commented

Have a look at the training documentation: https://trankit.readthedocs.io/en/latest/training.html
You could try to train a customized pipeline.

  • 👍1