Description
Pretrained DistilBertForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.distilbert_base_uncased_finetuned_ner_prao is a English model originally trained by prao.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("documents")
tokenClassifier = DistilBertForTokenClassification.pretrained("distilbert_base_uncased_finetuned_ner_prao","en") \
.setInputCols(["documents","token"]) \
.setOutputCol("ner")
pipeline = Pipeline().setStages([documentAssembler, tokenClassifier])
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("embeddings")
val tokenClassifier = DistilBertForTokenClassification
.pretrained("distilbert_base_uncased_finetuned_ner_prao", "en")
.setInputCols(Array("documents","token"))
.setOutputCol("ner")
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenClassifier))
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)
Model Information
| Model Name: | distilbert_base_uncased_finetuned_ner_prao |
| Compatibility: | Spark NLP 5.2.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [documents, token] |
| Output Labels: | [ner] |
| Language: | en |
| Size: | 247.3 MB |
References
https://huggingface.co/prao/distilbert-base-uncased-finetuned-ner