Recognize Entities DL pipeline for French - Large

Description

The entity_recognizer_lg is a pretrained pipeline that we can use to process text with a simple pipeline that performs basic processing steps and recognizes entities . It performs most of the common text processing tasks on your dataframe

Predicted Entities

Download Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipelinein
pipeline = PretrainedPipeline('entity_recognizer_lg', lang = 'fr')
annotations =  pipeline.fullAnnotate(""Bonjour de John Snow Labs! "")[0]
annotations.keys()
val pipeline = new PretrainedPipeline("entity_recognizer_lg", lang = "fr")
val result = pipeline.fullAnnotate("Bonjour de John Snow Labs! ")(0)
import nlu
text = [""Bonjour de John Snow Labs! ""]
result_df = nlu.load('fr.ner').predict(text)
result_df

Results

Results


|    | document                        | sentence                       | token                                      | embeddings                   | ner                                   | entities            |
|---:|:--------------------------------|:-------------------------------|:-------------------------------------------|:-----------------------------|:--------------------------------------|:--------------------|
|  0 | ['Bonjour de John Snow Labs! '] | ['Bonjour de John Snow Labs!'] | ['Bonjour', 'de', 'John', 'Snow', 'Labs!'] | [[-0.010997000150382,.,...]] | ['O', 'O', 'I-PER', 'I-PER', 'I-PER'] | ['John Snow Labs!'] |


{:.model-param}

Model Information

Model Name: entity_recognizer_lg
Type: pipeline
Compatibility: Spark NLP 4.4.2+
License: Open Source
Edition: Official
Language: fr
Size: 2.5 GB

Included Models

  • DocumentAssembler
  • SentenceDetector
  • TokenizerModel
  • WordEmbeddingsModel
  • NerDLModel
  • NerConverter