Description
Pretrained BertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.mbert_bengali_tydiqa_qa_finetuned_rqa_factoid_pipeline is a Bengali model originally trained by AsifAbrar6.
How to use
pipeline = PretrainedPipeline("mbert_bengali_tydiqa_qa_finetuned_rqa_factoid_pipeline", lang = "bn")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("mbert_bengali_tydiqa_qa_finetuned_rqa_factoid_pipeline", lang = "bn")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | mbert_bengali_tydiqa_qa_finetuned_rqa_factoid_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | bn |
| Size: | 625.5 MB |
References
https://huggingface.co/AsifAbrar6/mbert-bengali-tydiqa-qa-finetuned-RQA-factoid
Included Models
- MultiDocumentAssembler
- BertForQuestionAnswering