Malayalam XlmRobertaForSequenceClassification Cased model (from Hate-speech-CNERG)

Description

Pretrained XlmRobertaForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. deoffxlmr-mono-malyalam is a Malayalam model originally trained by Hate-speech-CNERG.

Predicted Entities

Not_offensive, Off_target_group, Profanity, Off_target_ind, Not_in_intended_language

Download Copy S3 URI

How to use

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

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

seq_classifier = XlmRoBertaForSequenceClassification.pretrained("xlmroberta_classifier_deoffxlmr_mono_malyalam","ml") \
    .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 = XlmRoBertaForSequenceClassification.pretrained("xlmroberta_classifier_deoffxlmr_mono_malyalam","ml")
    .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("ml.classify.xlmr_roberta").predict("""PUT YOUR STRING HERE""")

Model Information

Model Name: xlmroberta_classifier_deoffxlmr_mono_malyalam
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [class]
Language: ml
Size: 1.0 GB

References

References

  • https://huggingface.co/Hate-speech-CNERG/deoffxlmr-mono-malyalam
  • https://www.aclweb.org/anthology/2021.dravidianlangtech-1.38/