YAML Metadata
Error:
"datasets[0]" with value "SUC 3.0" is not valid. If possible, use a dataset id from https://hf.co/datasets.
Published with ❤️ from londogard.
Swedish NER in Flair (SUC 3.0)
F1-Score: 85.6 (SUC 3.0)
Predicts 8 tags:
Tag | Meaning |
---|---|
PRS | person name |
ORG | organisation name |
TME | time unit |
WRK | building name |
LOC | location name |
EVN | event name |
MSR | measurement unit |
OBJ | object (like "Rolls-Royce" is a object in the form of a special car) |
Based on Flair embeddings and LSTM-CRF.
Demo: How to use in Flair
Requires: Flair (pip install flair
)
from flair.data import Sentence
from flair.models import SequenceTagger
# load tagger
tagger = SequenceTagger.load("londogard/flair-swe-ner")
# make example sentence
sentence = Sentence("Hampus bor i Skåne och har levererat denna model idag.")
# predict NER tags
tagger.predict(sentence)
# print sentence
print(sentence)
# print predicted NER spans
print('The following NER tags are found:')
# iterate over entities and print
for entity in sentence.get_spans('ner'):
print(entity)
This yields the following output:
Span [0]: "Hampus" [− Labels: PRS (1.0)]
Span [3]: "Skåne" [− Labels: LOC (1.0)]
Span [9]: "idag" [− Labels: TME(1.0)]
So, the entities "Hampus" (labeled as a PRS), "Skåne" (labeled as a LOC), "idag" (labeled as a TME) are found in the sentence "Hampus bor i Skåne och har levererat denna model idag.".
Please mention londogard if using this models.
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.