Korean ElectraForSequenceClassification Base Cased model (from JminJ)

Description

Pretrained ElectraForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. tunibElectra_base_Bad_Sentence_Classifier is a Korean model originally trained by JminJ.

Predicted Entities

ok_sen, bad_sen

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 = BertForSequenceClassification.pretrained("electra_classifier_tunib_base_bad_sentence","ko") \
    .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 = BertForSequenceClassification.pretrained("electra_classifier_tunib_base_bad_sentence","ko")
    .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("ko.classify.electra.tunib.base.by_jminj").predict("""PUT YOUR STRING HERE""")

Model Information

References

• https://huggingface.co/JminJ/tunibElectra_base_Bad_Sentence_Classifier
• https://github.com/smilegate-ai/korean_unsmile_dataset
• https://github.com/kocohub/korean-hate-speech
• https://github.com/Beomi/KcELECTRA
• https://github.com/monologg/KoELECTRA
• https://github.com/JminJ/Bad_text_classifier
• https://github.com/Beomi/KcELECTRA
• https://github.com/monologg/KoELECTRA
• https://github.com/smilegate-ai/korean_unsmile_dataset
• https://github.com/kocohub/korean-hate-speech
• https://arxiv.org/abs/2003.10555