Edit on GitHub
  • John Snow Labs
  • Mar 17, 2023

English BertForSequenceClassification Cased model (from jakelever)

  • en
  • open_source
  • bert
  • sequence_classification
  • ner
  • tensorflow

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. coronabert is a English model originally trained by jakelever.

Predicted Entities

Non-human, Misinformation, Prevalence, Vaccines, News, Health Policy, Immunology, Inequality, Meta-analysis, Imaging, Infection Reports, Effect on Medical Specialties, Drug Targets, Transmission, Prevention, Education, Pediatrics, Medical Devices, Clinical Reports, Therapeutics, Communication, Non-medical, Long Haul, Review, Molecular Biology, Psychology, Diagnostics, Recommendations, Risk Factors, Comment/Editorial, Surveillance, Contact Tracing, Forecasting & Modelling, Healthcare Workers, Model Systems & Tools

Download Copy S3 URI

How to use

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

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

sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_coronabert","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

pipeline = Pipeline(stages=[documentAssembler, tokenizer, sequenceClassifier])

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

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

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

val tokenizer = new Tokenizer()
    .setInputCols("document")
    .setOutputCol("token")

val sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_coronabert","en")
    .setInputCols(Array("document", "token"))
    .setOutputCol("ner")

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

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

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

Model Information

Model Name: bert_sequence_classifier_coronabert
Compatibility: Spark NLP 4.3.1+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [ner]
Language: en
Size: 411.0 MB
Case sensitive: true
Max sentence length: 128

References

  • https://huggingface.co/jakelever/coronabert
  • https://coronacentral.ai
  • https://github.com/jakelever/corona-ml
  • https://github.com/jakelever/corona-ml/blob/master/stepByStep.md
  • https://doi.org/10.1101/2020.12.21.423860
  • https://github.com/jakelever/corona-ml/blob/master/machineLearningDetails.md
  • https://colab.research.google.com/drive/1cBNgKd4o6FNWwjKXXQQsC_SaX1kOXDa4?usp=sharing
  • https://colab.research.google.com/drive/1h7oJa2NDjnBEoox0D5vwXrxiCHj3B1kU?usp=sharing
  • https://github.com/jakelever/corona-ml/tree/master/category_prediction
  • https://github.com/jakelever/corona-ml/blob/master/category_prediction/annotated_documents.json.gz
  • https://github.com/jakelever/corona-ml/blob/master/stepByStep.md