Edit on GitHub
  • John Snow Labs
  • Nov 12, 2023

Spanish BertForQuestionAnswering Base Uncased model (from stevemobs)

  • es
  • open_source
  • bert
  • question_answering
  • onnx

Description

Pretrained Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-base-spanish-wwm-uncased-finetuned-squad_es is a Spanish model originally trained by stevemobs.

Predicted Entities

Download Copy S3 URI

How to use

documentAssembler = MultiDocumentAssembler() \
    .setInputCols(["question", "context"]) \
    .setOutputCols(["document_question", "document_context"])

spanClassifier = BertForQuestionAnswering.pretrained("bert_qa_base_spanish_wwm_uncased_finetuned_squad","es") \
    .setInputCols(["document_question", "document_context"]) \
    .setOutputCol("answer")\
    .setCaseSensitive(True)

pipeline = Pipeline(stages=[documentAssembler, spanClassifier])

data = spark.createDataFrame([["¿Cuál es mi nombre?", "Mi nombre es Clara y vivo en Berkeley."]]).toDF("question", "context")

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

val documentAssembler = new MultiDocumentAssembler()
      .setInputCols(Array("question", "context"))
      .setOutputCols(Array("document_question", "document_context"))

val spanClassifer = BertForQuestionAnswering.pretrained("bert_qa_base_spanish_wwm_uncased_finetuned_squad","es")
    .setInputCols(Array("document", "token"))
    .setOutputCol("answer")
    .setCaseSensitive(true)

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

val data = Seq("¿Cuál es mi nombre?", "Mi nombre es Clara y vivo en Berkeley.").toDF("question", "context")

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

import nlu
nlu.load("es.answer_question.bert.squad_es.uncased_base_finetuned").predict("""¿Cuál es mi nombre?", "Mi nombre es Clara y vivo en Berkeley.""")

Model Information

Model Name: bert_qa_base_spanish_wwm_uncased_finetuned_squad
Compatibility: Spark NLP 5.2.0+
License: Open Source
Edition: Official
Input Labels: [document_question, document_context]
Output Labels: [answer]
Language: es
Size: 409.7 MB
Case sensitive: false
Max sentence length: 512

References

References

  • https://huggingface.co/stevemobs/bert-base-spanish-wwm-uncased-finetuned-squad_es