English RoBertaForSequenceClassification Cased model (from unitary)

Description

Pretrained RoBertaForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. unbiased-toxic-roberta is a English model originally trained by unitary.

Predicted Entities

christian, jewish, homosexual_gay_or_lesbian, black, threat, female, toxicity, white, muslim, identity_attack, severe_toxicity, psychiatric_or_mental_illness, sexual_explicit, insult, male, obscene

Live Demo Open in Colab Download Copy S3 URI

How to use

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

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

seq_classifier = RoBertaForSequenceClassification.pretrained("roberta_classifier_unbiased_toxic","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

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

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

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

val documentAssembler = new DocumentAssembler()
      .setInputCols(Array("text"))
      .setOutputCols(Array("document"))

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

val seq_classifier = RoBertaForSequenceClassification.pretrained("roberta_classifier_unbiased_toxic","en")
    .setInputCols(Array("document", "token"))
    .setOutputCol("class")

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

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

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

import nlu
nlu.load("en.classify.roberta.by_unitary").predict("""PUT YOUR STRING HERE""")

Model Information

References

References

• https://huggingface.co/unitary/unbiased-toxic-roberta
• https://github.com/unitaryai/detoxify
• https://laurahanu.github.io/
• https://www.unitary.ai/
• https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge
• https://homes.cs.washington.edu/~msap/pdfs/sap2019risk.pdf
• https://arxiv.org/pdf/1703.04009.pdf%201.pdf
• https://arxiv.org/pdf/1905.12516.pdf