English BertForSequenceClassification Uncased model (from jonaskoenig)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. xtremedistil-l6-h256-uncased-go-emotion is a English model originally trained by jonaskoenig.

Predicted Entities

admiration, disappointment, disgust, surprise, optimism, remorse, disapproval, anger, sadness, amusement, excitement, joy, embarrassment, love, confusion, fear, approval, gratitude, neutral, caring, desire, nervousness, grief, realization, curiosity, annoyance, pride, relief

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_xtremedistil_l6_h256_uncased_go_emotion","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_xtremedistil_l6_h256_uncased_go_emotion","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.go_emotions.xtremedistiled_uncased").predict("""PUT YOUR STRING HERE""")

Model Information

Model Name: bert_classifier_xtremedistil_l6_h256_uncased_go_emotion
Compatibility: Spark NLP 4.2.0+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [class]
Language: en
Size: 47.6 MB
Case sensitive: false
Max sentence length: 256

References

  • https://huggingface.co/jonaskoenig/xtremedistil-l6-h256-uncased-go-emotion