Edit on GitHub
  • John Snow Labs
  • May 21, 2025

Arabic xlm_roberta_qa_xlm_roberta_base_arabic_pipeline pipeline XlmRoBertaForQuestionAnswering from bhavikardeshna

  • ar
  • open_source
  • pipeline
  • onnx

Description

Pretrained XlmRoBertaForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.xlm_roberta_qa_xlm_roberta_base_arabic_pipeline is a Arabic model originally trained by bhavikardeshna.

Predicted Entities

Download Copy S3 URI

How to use

pipeline = PretrainedPipeline("xlm_roberta_qa_xlm_roberta_base_arabic_pipeline", lang = "ar")
annotations =  pipeline.transform(df)

val pipeline = new PretrainedPipeline("xlm_roberta_qa_xlm_roberta_base_arabic_pipeline", lang = "ar")
val annotations = pipeline.transform(df)

Model Information

Model Name: xlm_roberta_qa_xlm_roberta_base_arabic_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: ar
Size: 884.0 MB

References

References

https://huggingface.co/bhavikardeshna/xlm-roberta-base-arabic

Included Models

  • MultiDocumentAssembler
  • XlmRoBertaForQuestionAnswering