Arabic BertForSequenceClassification Cased model (from Ammar-alhaj-ali)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. arabic-MARBERT-dialect-identification-city is a Arabic model originally trained by Ammar-alhaj-ali.

Predicted Entities

Riyadh, Fes, Doha, Beirut, Baghdad, Basra, Benghazi, Tunis, Algiers, Alexandria, Rabat, Khartoum, Aleppo, Tripoli, Jerusalem, Mosul, MSA, Jeddah, Aswan, Amman, Muscat, Salt, Damascus, Cairo, Sanaa, Sfax

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("bert_classifier_arabic_marbert_dialect_identification_city","ar") \
    .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("bert_classifier_arabic_marbert_dialect_identification_city","ar")
    .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("ar.classify.bert").predict("""PUT YOUR STRING HERE""")

Model Information

References

References

• https://huggingface.co/Ammar-alhaj-ali/arabic-MARBERT-dialect-identification-city
• https://camel.abudhabi.nyu.edu/madar-shared-task-2019/