Description
Pretrained BertForTokenClassification, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.bert_token_classifier_adres_ner_v12_pipeline is a Turkish model originally trained by deprem-ml.
How to use
pipeline = PretrainedPipeline("bert_token_classifier_adres_ner_v12_pipeline", lang = "tr")
annotations = pipeline.transform(df)
val pipeline = new PretrainedPipeline("bert_token_classifier_adres_ner_v12_pipeline", lang = "tr")
val annotations = pipeline.transform(df)
Model Information
| Model Name: | bert_token_classifier_adres_ner_v12_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | tr |
| Size: | 412.4 MB |
References
https://huggingface.co/deprem-ml/adres_ner_v12
Included Models
- DocumentAssembler
- TokenizerModel
- BertForTokenClassification