Description
Pretrained BertForQuestionAnswering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_qa_base_uncased_squadv1_x1.16_f88.1_d8_unstruct_v1 is a English model originally trained by madlag.
How to use
document_assembler = MultiDocumentAssembler() \
.setInputCol(["question", "context"]) \
.setOutputCol(["document_question", "document_context"])
spanClassifier = BertForQuestionAnswering.pretrained("bert_qa_base_uncased_squadv1_x1.16_f88.1_d8_unstruct_v1","en") \
.setInputCols(["document_question","document_context"]) \
.setOutputCol("answer")
pipeline = Pipeline().setStages([document_assembler, spanClassifier])
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)
val document_assembler = new MultiDocumentAssembler()
.setInputCol(Array("question", "context"))
.setOutputCol(Array("document_question", "document_context"))
val spanClassifier = BertForQuestionAnswering
.pretrained("bert_qa_base_uncased_squadv1_x1.16_f88.1_d8_unstruct_v1", "en")
.setInputCols(Array("document_question","document_context"))
.setOutputCol("answer")
val pipeline = new Pipeline().setStages(Array(document_assembler, spanClassifier))
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)
Model Information
| Model Name: | bert_qa_base_uncased_squadv1_x1.16_f88.1_d8_unstruct_v1 |
| Compatibility: | Spark NLP 5.2.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document_question, document_context] |
| Output Labels: | [answer] |
| Language: | en |
| Size: | 145.2 MB |
| Case sensitive: | false |
| Max sentence length: | 512 |
References
https://huggingface.co/madlag/bert-base-uncased-squadv1-x1.16-f88.1-d8-unstruct-v1