Edit on GitHub
  • John Snow Labs
  • Sep 03, 2024

Multilingual answer_finder_v1_l_multilingual_pipeline pipeline BertForQuestionAnswering from sinequa

  • xx
  • open_source
  • pipeline
  • onnx

Description

Pretrained BertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.answer_finder_v1_l_multilingual_pipeline is a Multilingual model originally trained by sinequa.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("answer_finder_v1_l_multilingual_pipeline", lang = "xx")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("answer_finder_v1_l_multilingual_pipeline", lang = "xx")
val annotations = pipeline.transform(df)

Model Information

Model Name: answer_finder_v1_l_multilingual_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.0+
License: Open Source
Edition: Official
Language: xx
Size: 464.4 MB

References

https://huggingface.co/sinequa/answer-finder-v1-L-multilingual

Included Models

  • MultiDocumentAssembler
  • BertForQuestionAnswering