English RobertaForSequenceClassification Cased model (from niksmer)

Description

Pretrained RobertaForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. PolicyBERTa-7d is a English model originally trained by niksmer.

Predicted Entities

welfare and quality of life, fabric of society, external relations, freedom and democracy, economy, political system, social groups

Live Demo Open in Colab Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("document")

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")

seq_classifier = RoBertaForSequenceClassification.pretrained("roberta_classifier_policyberta_7d","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

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

data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")

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

val documentAssembler = new DocumentAssembler()
      .setInputCols(Array("text"))
      .setOutputCols(Array("document"))

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

val seq_classifier = RoBertaForSequenceClassification.pretrained("roberta_classifier_policyberta_7d","en")
    .setInputCols(Array("document", "token"))
    .setOutputCol("class")

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

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

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

import nlu
nlu.load("en.classify.policyberta.by_niksmer").predict("""PUT YOUR STRING HERE""")

Model Information

References

References

• https://huggingface.co/niksmer/PolicyBERTa-7d
• https://manifesto-project.wzb.eu/
• https://manifesto-project.wzb.eu/datasets
• https://manifesto-project.wzb.eu/down/papers/handbook_2021_version_5.pdf
• https://manifesto-project.wzb.eu/down/tutorials/main-dataset.html#measuring-parties-left-right-positions