Description
Pretrained BertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.meda_bert_pipeline is a Danish model originally trained by Den-Intelligente-Patientjournal.
How to use
pipeline = PretrainedPipeline("meda_bert_pipeline", lang = "da")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("meda_bert_pipeline", lang = "da")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | meda_bert_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Language: | da |
| Size: | 412.3 MB |
References
https://huggingface.co/Den-Intelligente-Patientjournal/MeDa-BERT
Included Models
- DocumentAssembler
- TokenizerModel
- BertEmbeddings