Description
Pretrained Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-base-italian-uncased-squad-it is a Italian model orginally trained by antoniocappiello.
How to use
document_assembler = MultiDocumentAssembler() \
.setInputCols(["question", "context"]) \
.setOutputCols(["document_question", "document_context"])
spanClassifier = BertForQuestionAnswering.pretrained("bert_qa_bert_base_italian_uncased_squad_it_antoniocappiello","it") \
.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 = BertForQuestionAnswering
.pretrained("bert_qa_bert_base_italian_uncased_squad_it_antoniocappiello","it")
.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("it.answer_question.squad.bert.base_uncased").predict("""What's my name?|||"My name is Clara and I live in Berkeley.""")
Model Information
| Model Name: | bert_qa_bert_base_italian_uncased_squad_it_antoniocappiello |
| Compatibility: | Spark NLP 4.0.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [embeddings] |
| Language: | it |
| Size: | 410.3 MB |
| Case sensitive: | false |
| Max sentence length: | 512 |
References
- https://huggingface.co/antoniocappiello/bert-base-italian-uncased-squad-it
- http://sag.art.uniroma2.it/demo-software/squadit/
- https://github.com/crux82/squad-it/blob/master/README.md#evaluating-a-neural-model-over-squad-it