Description
Pretrained Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. squad_it_xxl_cased_hub1 is a Italian model originally trained by luigisaetta.
How to use
documentAssembler = MultiDocumentAssembler() \
.setInputCols(["question", "context"]) \
.setOutputCols(["document_question", "document_context"])
spanClassifier = BertForQuestionAnswering.pretrained("bert_qa_squad_xxl_cased_hub1","it") \
.setInputCols(["document_question", "document_context"]) \
.setOutputCol("answer")\
.setCaseSensitive(True)
pipeline = Pipeline(stages=[documentAssembler, spanClassifier])
data = spark.createDataFrame([["Qual è il mio nome?", "Mi chiamo Clara e vivo a Berkeley."]]).toDF("question", "context")
result = pipeline.fit(data).transform(data)
Model Information
| Model Name: | bert_qa_squad_xxl_cased_hub1 |
| Compatibility: | Spark NLP 4.0.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document_question, document_context] |
| Output Labels: | [answer] |
| Language: | it |
| Size: | 413.3 MB |
| Case sensitive: | true |
| Max sentence length: | 512 |
References
- https://huggingface.co/luigisaetta/squad_it_xxl_cased_hub1
- https://github.com/luigisaetta/nlp-qa-italian/blob/main/train_squad_it_final1.ipynb