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

English bert_qa_base_uncased_squadv1_x2.32_f86.6_d15_hybrid_v1 BertForQuestionAnswering from madlag

  • bert
  • en
  • open_source
  • question_answering
  • onnx

Description

Pretrained BertForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_qa_base_uncased_squadv1_x2.32_f86.6_d15_hybrid_v1 is a English model originally trained by madlag.

Download Copy S3 URI

How to use



document_assembler = MultiDocumentAssembler() \
    .setInputCol(["question", "context"]) \
    .setOutputCol(["document_question", "document_context"])
    
    
spanClassifier = BertForQuestionAnswering.pretrained("bert_qa_base_uncased_squadv1_x2.32_f86.6_d15_hybrid_v1","en") \
            .setInputCols(["document_question","document_context"]) \
            .setOutputCol("answer")

pipeline = Pipeline().setStages([document_assembler, spanClassifier])

pipelineModel = pipeline.fit(data)

pipelineDF = pipelineModel.transform(data)




val document_assembler = new MultiDocumentAssembler()
    .setInputCol(Array("question", "context")) 
    .setOutputCol(Array("document_question", "document_context"))
    
val spanClassifier = BertForQuestionAnswering  
    .pretrained("bert_qa_base_uncased_squadv1_x2.32_f86.6_d15_hybrid_v1", "en")
    .setInputCols(Array("document_question","document_context")) 
    .setOutputCol("answer") 

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

val pipelineModel = pipeline.fit(data)

val pipelineDF = pipelineModel.transform(data)

Model Information

Model Name: bert_qa_base_uncased_squadv1_x2.32_f86.6_d15_hybrid_v1
Compatibility: Spark NLP 5.2.0+
License: Open Source
Edition: Official
Input Labels: [document_question, document_context]
Output Labels: [answer]
Language: en
Size: 148.0 MB
Case sensitive: false
Max sentence length: 512

References

https://huggingface.co/madlag/bert-base-uncased-squadv1-x2.32-f86.6-d15-hybrid-v1