Description
Pretrained Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. roberta-base-ca-cased-qa is a Catalan model originally trained by projecte-aina.
How to use
document_assembler = MultiDocumentAssembler() \
.setInputCols(["question", "context"]) \
.setOutputCols(["document_question", "document_context"])
spanClassifier = RoBertaForQuestionAnswering.pretrained("roberta_qa_roberta_base_ca_cased_qa","ca") \
.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("question", "context")
.setOutputCols("document_question", "document_context")
val spanClassifier = RoBertaForQuestionAnswering
.pretrained("roberta_qa_roberta_base_ca_cased_qa","ca")
.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("ca.answer_question.roberta.base_cased").predict("""What's my name?|||"My name is Clara and I live in Berkeley.""")
Model Information
| Model Name: | roberta_qa_roberta_base_ca_cased_qa |
| Compatibility: | Spark NLP 4.0.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [question, context] |
| Output Labels: | [answer] |
| Language: | ca |
| Size: | 451.1 MB |
| Case sensitive: | true |
| Max sentence length: | 512 |
References
- https://huggingface.co/projecte-aina/roberta-base-ca-cased-qa
- https://arxiv.org/abs/1907.11692
- https://github.com/projecte-aina/club