Description
Pretrained RobertaForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bertin-base-ner-conll2002-es is a Spanish model originally trained by bertin-project.
Predicted Entities
MISC, LOC, PER, ORG
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")
tokenClassifier = RobertaForTokenClassification.pretrained("roberta_token_classifier_bertin_base_ner_conll2002","es") \
.setInputCols(["document", "token"]) \
.setOutputCol("ner")
pipeline = Pipeline(stages=[documentAssembler, tokenizer, tokenClassifier])
data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")
result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols("document")
.setOutputCol("token")
val tokenClassifier = RobertaForTokenClassification.pretrained("roberta_token_classifier_bertin_base_ner_conll2002","es")
.setInputCols(Array("document", "token"))
.setOutputCol("ner")
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, tokenClassifier))
val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
Model Information
| Model Name: | roberta_token_classifier_bertin_base_ner_conll2002 |
| Compatibility: | Spark NLP 4.3.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [ner] |
| Language: | es |
| Size: | 426.2 MB |
| Case sensitive: | true |
| Max sentence length: | 128 |
References
- https://huggingface.co/bertin-project/bertin-base-ner-conll2002-es