I am trying to process Portuguese text, but I’ve noticed there are no entity taggers for that language.
- Is it possible to train a model for Portuguese text? (Stanford or other nodes)
- Is there any pretrained POS tagger that can be used in Portuguese?
from the Stanford NLP pages I’ve found a link to the LX Center: http://lxcenter.di.fc.ul.pt/tools/en/
The tools provided are not integrated in KNIME, but you might be able to make use of them with external tool node anyway.
Thanks. Another way to go maybe to rely in vector models, which are language independent.