Description
Pretrained AlbertForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.albert_large_v2_ner_conll2003 is a English model originally trained by Gladiator.
How to use
document_assembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("documents")
sequenceClassifier = AlbertForTokenClassification.pretrained("albert_large_v2_ner_conll2003","en") \
.setInputCols(["documents","token"]) \
.setOutputCol("ner")
pipeline = Pipeline().setStages([document_assembler, sequenceClassifier])
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)
val document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("embeddings")
val sequenceClassifier = AlbertForTokenClassification
.pretrained("albert_large_v2_ner_conll2003", "en")
.setInputCols(Array("documents","token"))
.setOutputCol("ner")
val pipeline = new Pipeline().setStages(Array(document_assembler, sequenceClassifier))
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)
Model Information
| Model Name: | albert_large_v2_ner_conll2003 |
| Compatibility: | Spark NLP 5.1.2+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [documents, token] |
| Output Labels: | [ner] |
| Language: | en |
| Size: | 62.8 MB |
References
https://huggingface.co/Gladiator/albert-large-v2_ner_conll2003