Swedish BertForTokenClassification Base Cased model (from KBLab)

Description

Pretrained BertForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-base-swedish-cased-neriob is a Swedish model originally trained by KBLab.

Predicted Entities

PER, LOC, LOCORG, EVN, TME, WRK, MSR, OBJ, PRSWRK, OBJORG, ORG, ORGPRS, LOCPRS

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_swedish_cased_neriob","sv") \
    .setInputCols(["sentence", "token"]) \
    .setOutputCol("ner")

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

data = spark.createDataFrame([["Jag älskar Spark NLP"]]).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_swedish_cased_neriob","sv")
    .setInputCols(Array("sentence", "token"))
    .setOutputCol("ner")

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

val data = Seq("Jag älskar Spark NLP").toDF("text")

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

import nlu
nlu.load("sv.ner.bert.cased_base.neriob.by_kblab").predict("""Jag älskar Spark NLP""")

Model Information

Model Name:	bert_ner_bert_base_swedish_cased_neriob
Compatibility:	Spark NLP 4.0.0+
License:	Open Source
Edition:	Official
Input Labels:	[document, token]
Output Labels:	[ner]
Language:	sv
Size:	465.8 MB
Case sensitive:	true
Max sentence length:	128

References

https://huggingface.co/KBLab/bert-base-swedish-cased-neriob

PREVIOUSEnglish BertForTokenClassification Cased model (from balamurugan1603)

NEXTTurkish BertForTokenClassification Base Cased model (from beyhan)