Persian Named Entity Recognition (from HooshvareLab)

Description

Pretrained Named Entity Recognition model, uploaded to Hugging Face, adapted and imported into Spark NLP. bert-base-parsbert-ner-uncased is a Persian model orginally trained by HooshvareLab.

Predicted Entities

percent, facility, location, money, product, person, date, organization, time, event

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_parsbert_ner_uncased","fa") \
    .setInputCols(["sentence", "token"]) \
    .setOutputCol("ner")

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

data = spark.createDataFrame([["من عاشق جرقه nlp هستم"]]).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_parsbert_ner_uncased","fa") 
    .setInputCols(Array("sentence", "token")) 
    .setOutputCol("ner")

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

val data = Seq("من عاشق جرقه nlp هستم").toDF("text")

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

Model Information

Model Name: bert_ner_bert_base_parsbert_ner_uncased
Compatibility: Spark NLP 3.4.2+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [ner]
Language: fa
Size: 607.1 MB
Case sensitive: true
Max sentence length: 128

References

  • https://huggingface.co/HooshvareLab/bert-base-parsbert-ner-uncased
  • https://arxiv.org/abs/2005.12515
  • http://nsurl.org/tasks/task-7-named-entity-recognition-ner-for-farsi/
  • https://github.com/HaniehP/PersianNER
  • https://github.com/hooshvare/parsbert-ner/blob/master/persian-ner-pipeline.ipynb
  • https://colab.research.google.com/github/hooshvare/parsbert-ner/blob/master/persian-ner-pipeline.ipynb
  • https://arxiv.org/abs/2005.12515
  • https://tensorflow.org/tfrc
  • https://hooshvare.com
  • https://www.linkedin.com/in/m3hrdadfi/
  • https://twitter.com/m3hrdadfi
  • https://github.com/m3hrdadfi
  • https://www.linkedin.com/in/mohammad-gharachorloo/
  • https://twitter.com/MGharachorloo
  • https://github.com/baarsaam
  • https://www.linkedin.com/in/marziehphi/
  • https://twitter.com/marziehphi
  • https://github.com/marziehphi
  • https://www.linkedin.com/in/mohammad-manthouri-aka-mansouri-07030766/
  • https://twitter.com/mmanthouri
  • https://github.com/mmanthouri
  • https://hooshvare.com/
  • https://www.linkedin.com/company/hooshvare
  • https://twitter.com/hooshvare
  • https://github.com/hooshvare
  • https://www.instagram.com/hooshvare/
  • https://www.linkedin.com/in/sara-tabrizi-64548b79/
  • https://www.behance.net/saratabrizi
  • https://www.instagram.com/sara_b_tabrizi/