Description
This pretrained pipeline is built on bert_token_classifier_scandi_ner model which is imported from HuggingFace.
Predicted Entities
How to use
scandiner_pipeline = PretrainedPipeline("bert_token_classifier_scandi_ner_pipeline", lang = "xx")
scandiner_pipeline.annotate("Hans er professor ved Statens Universitet, som ligger i København, og han er en rigtig københavner.")
val scandiner_pipeline = new PretrainedPipeline("bert_token_classifier_scandi_ner_pipeline", lang = "xx")
val scandiner_pipeline.annotate("Hans er professor ved Statens Universitet, som ligger i København, og han er en rigtig københavner.")
Results
Results
+-------------------+---------+
|chunk |ner_label|
+-------------------+---------+
|Hans |PER |
|Statens Universitet|ORG |
|København |LOC |
|københavner |MISC |
+-------------------+---------+
{:.model-param}
Model Information
| Model Name: | bert_token_classifier_scandi_ner_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 4.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | xx |
| Size: | 666.9 MB |
Included Models
- DocumentAssembler
- SentenceDetector
- TokenizerModel
- BertForTokenClassification
- NerConverter
- Finisher