Description
Pretrained DistilBERT NER model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. distilbert-base-multi-cased-finetuned-typo-detection is a Multilingual model originally trained by mrm8488.
Predicted Entities
ok, typo
How to use
documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
sentenceDetector = SentenceDetector()\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer() \
.setInputCols("sentence") \
.setOutputCol("token")
ner = DistilBertForTokenClassification.pretrained("distilbert_ner_base_multi_cased_finetuned_typo_detection","xx") \
.setInputCols(["sentence", "token"]) \
.setOutputCol("ner")
pipeline = Pipeline(stages=[documentAssembler, tokenizer, ner])
data = spark.createDataFrame([["PUT YOUR STRING HERE."]]).toDF("text")
result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentenceDetector = new SentenceDetector()
.setInputCols(Array("document"))
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols(Array("sentence"))
.setOutputCol("token")
val ner = DistilBertForTokenClassification.pretrained("distilbert_ner_base_multi_cased_finetuned_typo_detection","xx")
.setInputCols(Array("sentence", "token"))
.setOutputCol("ner")
val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, ner))
val data = Seq("PUT YOUR STRING HERE.").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("xx.ner.distil_bert.cased_base_finetuned").predict("""PUT YOUR STRING HERE.""")
Model Information
| Model Name: | distilbert_ner_base_multi_cased_finetuned_typo_detection |
| Compatibility: | Spark NLP 5.2.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [documents, token] |
| Output Labels: | [ner] |
| Language: | xx |
| Size: | 505.4 MB |
References
References
https://huggingface.co/mrm8488/distilbert-base-multi-cased-finetuned-typo-detection