Description
Pretrained Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert_uncased_L-2_H-128_A-2_squad2 is a English model originally trained by aodiniz.
Predicted Entities
How to use
documentAssembler = MultiDocumentAssembler() \
.setInputCols(["question", "context"]) \
.setOutputCols(["document_question", "document_context"])
spanClassifier = BertForQuestionAnswering.pretrained("bert_qa_uncased_l_2_h_128_a_2_squad2","en") \
.setInputCols(["document_question", "document_context"]) \
.setOutputCol("answer")\
.setCaseSensitive(True)
pipeline = Pipeline(stages=[documentAssembler, spanClassifier])
data = spark.createDataFrame([["What is my name?", "My name is Clara and I live in Berkeley."]]).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 = BertForQuestionAnswering.pretrained("bert_qa_uncased_l_2_h_128_a_2_squad2","en")
.setInputCols(Array("document", "token"))
.setOutputCol("answer")
.setCaseSensitive(true)
val pipeline = new Pipeline().setStages(Array(documentAssembler, spanClassifier))
val data = Seq("What is my name?", "My name is Clara and I live in Berkeley.").toDF("question", "context")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.answer_question.bert.squadv2.uncased_2l_128d_a2a_128d").predict("""What is my name?|||"My name is Clara and I live in Berkeley.""")
Model Information
| Model Name: | bert_qa_uncased_l_2_h_128_a_2_squad2 |
| Compatibility: | Spark NLP 5.2.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document_question, document_context] |
| Output Labels: | [answer] |
| Language: | en |
| Size: | 16.7 MB |
| Case sensitive: | false |
| Max sentence length: | 512 |
References
References
- https://huggingface.co/aodiniz/bert_uncased_L-2_H-128_A-2_squad2