The corpus holds 5127 sentences, annotated with 16 classes, with a total of 26376 annotated entities. The corpus comes into two formats: BRAT and CONLLUP.
# to train a new model on ronec python3 convert_spacy.py ronec/conllup/ronec.conllup output python3 -m spacy train ro models output/train_ronec.json output/train_ronec.json -p ent # download the Romanian NER model python -m spacy download ro_ner # load the model and print entities for a simple sentence import spacy nlp = spacy.load("ro_ner") doc = nlp("Popescu Ion a fost la Cluj") for ent in doc.ents: print(ent.text, ent.start_char, ent.end_char, ent.label_)
Stefan Daniel Dumitrescu, Andrei-Marius Avram
Submit your project
If you have a project that you want the spaCy community to make use of, you can suggest it by submitting a pull request to the spaCy website repository. The Universe database is open-source and collected in a simple JSON file. For more details on the formats and available fields, see the documentation. Looking for inspiration your own spaCy plugin or extension? Check out the
project idea label on the issue tracker.