Description
Pretrained Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. koelectra-base-v2-finetuned-korquad-384 is a Korean model originally trained by monologg.
How to use
documentAssembler = MultiDocumentAssembler() \
.setInputCols(["question", "context"]) \
.setOutputCols(["document_question", "document_context"])
spanClassifier = BertForQuestionAnswering.pretrained("electra_qa_base_v2_finetuned_korquad_384","ko") \
.setInputCols(["document_question", "document_context"]) \
.setOutputCol("answer")\
.setCaseSensitive(True)
pipeline = Pipeline(stages=[documentAssembler, spanClassifier])
data = spark.createDataFrame([["내 이름은 무엇입니까?", "제 이름은 클라라이고 저는 버클리에 살고 있습니다."]]).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("electra_qa_base_v2_finetuned_korquad_384","ko")
.setInputCols(Array("document", "token"))
.setOutputCol("answer")
.setCaseSensitive(true)
val pipeline = new Pipeline().setStages(Array(documentAssembler, spanClassifier))
val data = Seq("내 이름은 무엇입니까?", "제 이름은 클라라이고 저는 버클리에 살고 있습니다.").toDF("question", "context")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("ko.answer_question.korquad.electra.base_v2_384.by_monologg").predict("""내 이름은 무엇입니까?|||"제 이름은 클라라이고 저는 버클리에 살고 있습니다.""")
Model Information
| Model Name: | electra_qa_base_v2_finetuned_korquad_384 |
| Compatibility: | Spark NLP 4.0.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document_question, document_context] |
| Output Labels: | [answer] |
| Language: | ko |
| Size: | 412.4 MB |
| Case sensitive: | true |
| Max sentence length: | 512 |
References
- https://huggingface.co/monologg/koelectra-base-v2-finetuned-korquad-384