Edit on GitHub
  • John Snow Labs
  • Nov 06, 2023

English BertForTokenClassification Cased model (from connorboyle)

  • bert
  • ner
  • open_source
  • en
  • onnx

Description

Pretrained BertForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-ner-i2b2 is a English model originally trained by connorboyle.

Predicted Entities

STATE, ORGANIZATION, BIOID, HEALTHPLAN, PATIENT, COUNTRY, AGE, FAX, LOCATION, PHONE, IDNUM, DOCTOR, URL, DEVICE, STREET, DATE, ZIP, CITY, EMAIL, MEDICALRECORD, USERNAME, HOSPITAL, PROFESSION

Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
        .setInputCol("text") \
        .setOutputCol("document")

sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx")\
       .setInputCols(["document"])\
       .setOutputCol("sentence")

tokenizer = Tokenizer() \
    .setInputCols("sentence") \
    .setOutputCol("token")

tokenClassifier = BertForTokenClassification.pretrained("bert_ner_bert_ner_i2b2","en") \
    .setInputCols(["sentence", "token"]) \
    .setOutputCol("ner")

pipeline = Pipeline(stages=[documentAssembler, sentenceDetector, tokenizer, tokenClassifier])

data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")

result = pipeline.fit(data).transform(data)

val documentAssembler = new DocumentAssembler() 
          .setInputCol("text") 
          .setOutputCol("document")

val sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx")
       .setInputCols(Array("document"))
       .setOutputCol("sentence")

val tokenizer = new Tokenizer() 
    .setInputCols(Array("sentence"))
    .setOutputCol("token")
+
val tokenClassifier = BertForTokenClassification.pretrained("bert_ner_bert_ner_i2b2","en") 
    .setInputCols(Array("sentence", "token")) 
    .setOutputCol("ner")

val pipeline = new Pipeline().setStages(Array(documentAssembler,sentenceDetector, tokenizer, tokenClassifier))

val data = Seq("PUT YOUR STRING HERE").toDF("text")

val result = pipeline.fit(data).transform(data)

import nlu
nlu.load("en.ner.bert.by_connorboyle").predict("""PUT YOUR STRING HERE""")

Model Information

Model Name: bert_ner_bert_ner_i2b2
Compatibility: Spark NLP 5.2.0+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [ner]
Language: en
Size: 403.8 MB
Case sensitive: true
Max sentence length: 128

References

References

  • https://huggingface.co/connorboyle/bert-ner-i2b2