Hebrew BertForSequenceClassification Cased model (from avichr)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. heBERT_sentiment_analysis is a Hebrew model originally trained by avichr.

Predicted Entities

positive, negative, neutral

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_loaded = BertForSequenceClassification.pretrained("bert_classifier_he_sentiment_analysis","he") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

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

data = spark.createDataFrame([["אני אוהב את Spark NLP"]]).toDF("text")

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

val documentAssembler = new DocumentAssembler() 
          .setInputCol("text") 
          .setOutputCol("document")

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

val sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_he_sentiment_analysis","he") 
    .setInputCols(Array("document", "token")) 
    .setOutputCol("class")

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

val data = Seq("אני אוהב את Spark NLP").toDF("text")

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

Model Information

References

• https://huggingface.co/avichr/heBERT_sentiment_analysis
• https://arxiv.org/abs/1810.04805
• https://oscar-corpus.com/
• https://journals.sagepub.com/doi/pdf/10.1177/001316447003000105
• https://github.com/aws-samples/aws-lambda-docker-serverless-inference/tree/main/hebert-sentiment-analysis-inference-docker-lambda
• https://github.com/avichaychriqui/HeBERT