Description
Pretrained BertForQuestionAnswering, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_italian_xxl_cased_squad_italian_v1_pipeline is a Italian model originally trained by fabgraziano.
How to use
pipeline = PretrainedPipeline("bert_italian_xxl_cased_squad_italian_v1_pipeline", lang = "it")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("bert_italian_xxl_cased_squad_italian_v1_pipeline", lang = "it")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | bert_italian_xxl_cased_squad_italian_v1_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | it |
| Size: | 412.6 MB |
References
https://huggingface.co/fabgraziano/bert-italian-xxl-cased_squad-it_v1
Included Models
- MultiDocumentAssembler
- BertForQuestionAnswering