Spanish BertForSequenceClassification Cased model (from M47Labs)

Description

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

Predicted Entities

deportes, opinion, politica, medio_ambiente, educacion, cultura, ciencia_tecnologia, sociedad, clickbait, economia

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_spanish_news_classification_headlines_untrained","es") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

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

data = spark.createDataFrame([["Amo 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_spanish_news_classification_headlines_untrained","es") 
    .setInputCols(Array("document", "token")) 
    .setOutputCol("class")

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

val data = Seq("Amo Spark NLP").toDF("text")

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

import nlu
nlu.load("es.classify.bert.news.by_m47labs").predict("""Amo Spark NLP""")

Model Information

References

• https://huggingface.co/M47Labs/spanish_news_classification_headlines_untrained
• https://www.m47labs.com/es/
• https://colab.research.google.com/drive/1XsKea6oMyEckye2FePW_XN7Rf8v41Cw_?usp=sharing