Description
Pretrained DistilBERT Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. distilbert-multi-finedtuned-squad-pt is a Portuguese model originally trained by mrm8488.
How to use
documentAssembler = MultiDocumentAssembler() \
.setInputCols(["question", "context"]) \
.setOutputCols(["document_question", "document_context"])
spanClassifier = DistilBertForQuestionAnswering.pretrained("distilbert_qa_finetuned_squad","pt") \
.setInputCols(["document_question", "document_context"]) \
.setOutputCol("answer")\
.setCaseSensitive(True)
pipeline = Pipeline(stages=[documentAssembler, spanClassifier])
data = spark.createDataFrame([["PUT YOUR 'QUESTION' STRING HERE?", "PUT YOUR 'CONTEXT' STRING HERE"]]).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 = DistilBertForQuestionAnswering.pretrained("distilbert_qa_finetuned_squad","pt")
.setInputCols(Array("document", "token"))
.setOutputCol("answer")
.setCaseSensitive(true)
val pipeline = new Pipeline().setStages(Array(documentAssembler, spanClassifier))
val data = Seq("PUT YOUR 'QUESTION' STRING HERE?", "PUT YOUR 'CONTEXT' STRING HERE").toDS.toDF("question", "context")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("pt.answer_question.distil_bert.squad.finetuned").predict("""PUT YOUR 'QUESTION' STRING HERE?|||"PUT YOUR 'CONTEXT' STRING HERE""")
Model Information
| Model Name: | distilbert_qa_finetuned_squad |
| Compatibility: | Spark NLP 4.0.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document_question, document_context] |
| Output Labels: | [answer] |
| Language: | pt |
| Size: | 505.7 MB |
| Case sensitive: | true |
| Max sentence length: | 512 |
References
https://huggingface.co/mrm8488/distilbert-multi-finedtuned-squad-pt