Spanish RobertaForQuestionAnswering Large Cased model (from PlanTL-GOB-ES)

Description

Pretrained RobertaForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. roberta-large-bne-sqac is a Spanish model originally trained by PlanTL-GOB-ES.

Live Demo Open in Colab Download Copy S3 URI

How to use

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

Question_Answering = RoBertaForQuestionAnswering.pretrained("roberta_qa_plantl_gob_es_large_bne_s_c","es")\
     .setInputCols(["document_question", "document_context"])\
     .setOutputCol("answer")\
     .setCaseSensitive(True)
    
pipeline = Pipeline(stages=[Document_Assembler, Question_Answering])

data = spark.createDataFrame([["What's my name?","My name is Clara and I live in Berkeley."]]).toDF("question", "context")

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

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

val Question_Answering = RoBertaForQuestionAnswering.pretrained("roberta_qa_plantl_gob_es_large_bne_s_c","es")
     .setInputCols(Array("document_question", "document_context"))
     .setOutputCol("answer")
     .setCaseSensitive(True)
    
val pipeline = new Pipeline().setStages(Array(Document_Assembler, Question_Answering))

val data = Seq("What's my name?","My name is Clara and I live in Berkeley.").toDS.toDF("question", "context")

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

import nlu
nlu.load("es.answer_question.roberta.sqac.large.by_plantl_gob_es").predict("""What's my name?|||"My name is Clara and I live in Berkeley.""")

Model Information

References

• https://huggingface.co/PlanTL-GOB-ES/roberta-large-bne-sqac
• https://arxiv.org/abs/1907.11692
• http://www.bne.es/en/Inicio/index.html
• https://github.com/PlanTL-GOB-ES/lm-spanish
• https://www.apache.org/licenses/LICENSE-2.0
• http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/6405
• https://paperswithcode.com/sota?task=question-answering&dataset=SQAC