Persian BertForSequenceClassification Base Uncased model (from HooshvareLab)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-fa-base-uncased-clf-digimag is a Persian model originally trained by HooshvareLab.

Predicted Entities

عمومی, راهنمای خرید, بازی ویدیویی, هنر و سینما, علم و تکنولوژی, سلامت و زیبایی, کتاب و ادبیات

Live Demo Open in Colab 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_fa_base_uncased_clf_digimag","fa") \
    .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_fa_base_uncased_clf_digimag","fa")
    .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

References

• https://huggingface.co/HooshvareLab/bert-fa-base-uncased-clf-digimag
• https://github.com/hooshvare/parsbert
• https://www.digikala.com/mag/
• https://drive.google.com/uc?id=1YgrCYY-Z0h2z0-PfWVfOGt1Tv0JDI-qz
• https://colab.research.google.com/github/hooshvare/parsbert/blob/master/notebooks/Taaghche_Sentiment_Analysis.ipynb
• https://github.com/hooshvare/parsbert/issues