Description
This pretrained pipeline is built on the top of ner_deid_generic_bert model.
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("ner_deid_generic_bert_pipeline", "ro", "clinical/models")
text = '''Spitalul Pentru Ochi de Deal, Drumul Oprea Nr. 972 Vaslui, 737405 România
Tel: +40(235)413773
Data setului de analize: 25 May 2022 15:36:00
Nume si Prenume : BUREAN MARIA, Varsta: 77
Medic : Agota Evelyn Tımar
C.N.P : 2450502264401'''
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("ner_deid_generic_bert_pipeline", "ro", "clinical/models")
val text = "Spitalul Pentru Ochi de Deal, Drumul Oprea Nr. 972 Vaslui, 737405 România
Tel: +40(235)413773
Data setului de analize: 25 May 2022 15:36:00
Nume si Prenume : BUREAN MARIA, Varsta: 77
Medic : Agota Evelyn Tımar
C.N.P : 2450502264401"
val result = pipeline.fullAnnotate(text)
Results
| | ner_chunks | begin | end | ner_label | confidence |
|---:|:-----------------------------|--------:|------:|:------------|-------------:|
| 0 | Spitalul Pentru Ochi de Deal | 0 | 27 | LOCATION | 0.99352 |
| 1 | Drumul Oprea Nr. 972 | 30 | 49 | LOCATION | 0.99994 |
| 2 | Vaslui | 51 | 56 | LOCATION | 1 |
| 3 | 737405 | 59 | 64 | LOCATION | 1 |
| 4 | +40(235)413773 | 79 | 92 | CONTACT | 1 |
| 5 | 25 May 2022 | 119 | 129 | DATE | 1 |
| 6 | si | 145 | 146 | NAME | 0.9998 |
| 7 | BUREAN MARIA | 158 | 169 | NAME | 0.9993 |
| 8 | 77 | 180 | 181 | AGE | 1 |
| 9 | Agota Evelyn Tımar | 191 | 210 | NAME | 0.859975 |
| | C | | | | |
| 10 | 2450502264401 | 218 | 230 | ID | 1 |
Model Information
| Model Name: | ner_deid_generic_bert_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | ro |
| Size: | 483.8 MB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- BertEmbeddings
- MedicalNerModel
- NerConverterInternalModel