Description
Pretrained Question Answering model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. roberta-base-squad is a Catalan model originally trained by thatdramebaazguy.
How to use
document_assembler = MultiDocumentAssembler() \
.setInputCols(["question", "context"]) \
.setOutputCols(["document_question", "document_context"])
spanClassifier = RoBertaForQuestionAnswering.pretrained("roberta_qa_roberta_base_squad","ca") \
.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)
Model Information
| Model Name: | roberta_qa_roberta_base_squad |
| Compatibility: | Spark NLP 4.0.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [question, context] |
| Output Labels: | [answer] |
| Language: | ca |
| Size: | 461.6 MB |
| Case sensitive: | true |
| Max sentence length: | 512 |
References
- https://huggingface.co/thatdramebaazguy/roberta-base-squad