Hungarian BertForTokenClassification Base Cased model (from akdeniz27)

Description

Pretrained BertForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-base-hungarian-cased-ner is a Hungarian model originally trained by akdeniz27.

Predicted Entities

ORG, LOC, PER

Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
        .setInputCol("text") \
        .setOutputCol("document")

sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx")\
       .setInputCols(["document"])\
       .setOutputCol("sentence")

tokenizer = Tokenizer() \
    .setInputCols("sentence") \
    .setOutputCol("token")

tokenClassifier = BertForTokenClassification.pretrained("bert_ner_bert_base_hungarian_cased_ner","hu") \
    .setInputCols(["sentence", "token"]) \
    .setOutputCol("ner")

pipeline = Pipeline(stages=[documentAssembler, sentenceDetector, tokenizer, tokenClassifier])

data = spark.createDataFrame([["Szeretem a Spark NLP -t"]]).toDF("text")

result = pipeline.fit(data).transform(data)

val documentAssembler = new DocumentAssembler() 
          .setInputCol("text") 
          .setOutputCol("document")

val sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx")
       .setInputCols(Array("document"))
       .setOutputCol("sentence")

val tokenizer = new Tokenizer() 
    .setInputCols(Array("sentence"))
    .setOutputCol("token")

val tokenClassifier = BertForTokenClassification.pretrained("bert_ner_bert_base_hungarian_cased_ner","hu") 
    .setInputCols(Array("sentence", "token")) 
    .setOutputCol("ner")

val pipeline = new Pipeline().setStages(Array(documentAssembler,sentenceDetector, tokenizer, tokenClassifier))

val data = Seq("Szeretem a Spark NLP -t").toDF("text")

val result = pipeline.fit(data).transform(data)

import nlu
nlu.load("hu.ner.bert.cased_base.by_akdeniz27").predict("""Szeretem a Spark NLP -t""")

Model Information

Model Name:	bert_ner_bert_base_hungarian_cased_ner
Compatibility:	Spark NLP 4.0.0+
License:	Open Source
Edition:	Official
Input Labels:	[document, token]
Output Labels:	[ner]
Language:	hu
Size:	413.0 MB
Case sensitive:	true
Max sentence length:	128

References

https://huggingface.co/akdeniz27/bert-base-hungarian-cased-ner
https://aclanthology.org/P17-1178.pdf

PREVIOUSHungarian BertForTokenClassification Base Cased model (from fdominik98)

NEXTIndonesian BertForTokenClassification Base Cased model (from cahya)