English XlmRoBertaForQuestionAnswering (from deepset)

Description

Pretrained Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. xlm-roberta-large-squad2 is a English model originally trained by deepset.

Live Demo Open in Colab Download Copy S3 URICopied!

How to use

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

spanClassifier = XlmRoBertaForQuestionAnswering.pretrained("xlm_roberta_qa_xlm_roberta_large_squad2","en") \
.setInputCols(["document_question", "document_context"]) \
.setOutputCol("answer") \
.setCaseSensitive(True)

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

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

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

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

val spanClassifier = XlmRoBertaForQuestionAnswering
.pretrained("xlm_roberta_qa_xlm_roberta_large_squad2","en")
.setInputCols(Array("document_question", "document_context"))
.setOutputCol("answer")
.setCaseSensitive(true)
.setMaxSentenceLength(512)

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

val example = Seq(
("Where was John Lenon born?", "John Lenon was born in London and lived in Paris. My name is Sarah and I live in London."),
("What's my name?", "My name is Clara and I live in Berkeley."))
.toDF("question", "context")

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

import nlu
nlu.load("en.answer_question.squadv2.xlm_roberta.large").predict("""What's my name?|||"My name is Clara and I live in Berkeley.""")

Model Information

References

• https://huggingface.co/deepset/xlm-roberta-large-squad2
• https://worksheets.codalab.org/rest/bundles/0x6b567e1cf2e041ec80d7098f031c5c9e/contents/blob/
• https://www.linkedin.com/company/deepset-ai/
• https://twitter.com/deepset_ai
• http://www.deepset.ai/jobs
• https://haystack.deepset.ai/community/join
• https://public-mlflow.deepset.ai/#/experiments/124/runs/3a540e3f3ecf4dd98eae8fc6d457ff20
• https://github.com/deepset-ai/haystack/
• https://github.com/deepset-ai/FARM
• https://deepset.ai/germanquad
• https://github.com/deepmind/xquad
• https://deepset.ai
• https://deepset.ai/german-bert
• https://github.com/deepset-ai/haystack/discussions
• https://github.com/facebookresearch/MLQA