English BertForSequenceClassification Cased model (from LiYuan)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. amazon-review-sentiment-analysis is a English model originally trained by LiYuan.

Predicted Entities

3 stars, 4 stars, 2 stars, 5 stars, 1 star

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_amazon_review_sentiment_analysis","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

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

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(Array("document"))
    .setOutputCol("token")

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

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

val data = Seq("PUT YOUR STRING HERE").toDF("text")

val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.classify.bert.amazon_sentiment.").predict("""PUT YOUR STRING HERE""")

Model Information

Model Name: bert_classifier_amazon_review_sentiment_analysis
Compatibility: Spark NLP 4.2.0+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [class]
Language: en
Size: 628.3 MB
Case sensitive: true
Max sentence length: 256

References

  • https://huggingface.co/LiYuan/amazon-review-sentiment-analysis
  • https://www.kaggle.com/datasets/cynthiarempel/amazon-us-customer-reviews-dataset
  • https://github.com/vanderbilt-data-science/bigdata/blob/main/06-fine-tune-BERT-on-our-dataset.ipynb
  • https://www.kaggle.com/datasets/cynthiarempel/amazon-us-customer-reviews-dataset