Recognize Entities DL pipeline for English - BERT

Description

The recognize_entities_bert 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

Live Demo Open in Colab Download

How to use


from sparknlp.pretrained import PretrainedPipelinein
pipeline = PretrainedPipeline('recognize_entities_bert', lang = 'en')
annotations =  pipeline.fullAnnotate(""Hello from John Snow Labs ! "")[0]
annotations.keys()


val pipeline = new PretrainedPipeline("recognize_entities_bert", lang = "en")
val result = pipeline.fullAnnotate("Hello from John Snow Labs ! ")(0)



import nlu
text = [""Hello from John Snow Labs ! ""]
result_df = nlu.load('en.ner.bert').predict(text)
result_df
    

Results

|    | document                         | sentence                        | token                                          | embeddings                   | ner                                        | entities           |
|---:|:---------------------------------|:--------------------------------|:-----------------------------------------------|:-----------------------------|:-------------------------------------------|:-------------------|
|  0 | ['Hello from John Snow Labs ! '] | ['Hello from John Snow Labs !'] | ['Hello', 'from', 'John', 'Snow', 'Labs', '!'] | [[-0.085488274693489,.,...]] | ['O', 'O', 'I-PER', 'I-PER', 'I-ORG', 'O'] | ['John Snow Labs'] ||    | document                         | sentence                        | token                                          | embeddings                   | ner                                        | entities           |

Model Information

Model Name: recognize_entities_bert
Type: pipeline
Compatibility: Spark NLP 3.0.0+
License: Open Source
Edition: Official
Language: en