Description
Pretrained BertEmbeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_kor_base_pipeline is a Korean model originally trained by kykim.
How to use
pipeline = PretrainedPipeline("bert_kor_base_pipeline", lang = "ko")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("bert_kor_base_pipeline", lang = "ko")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | bert_kor_base_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Language: | ko |
| Size: | 441.2 MB |
References
https://huggingface.co/kykim/bert-kor-base
Included Models
- DocumentAssembler
- TokenizerModel
- BertEmbeddings