Multilingual BertForSequenceClassification Cased model (from M47Labs)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. english_news_classification_headlines is a Multilingual model originally trained by M47Labs.

Predicted Entities

arts, culture, entertainment and media, religion and belief, science and technology, economy, business and finance, conflict, war and peace, health, society, weather, enviroment, sport, politics, education, disaster, accident and emergency incident, lifestyle and leisure, crime, law and justice, labour

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_english_news_classification_headlines","xx") \
    .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_english_news_classification_headlines","xx") 
    .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("xx.classify.bert.news.").predict("""PUT YOUR STRING HERE""")

Model Information

References

• https://huggingface.co/M47Labs/english_news_classification_headlines