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-armanner-uncased is a Persian model orginally trained by HooshvareLab.

Predicted Entities

fac, pers, pro, event, org, loc

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_armanner_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_armanner_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_armanner_uncased
Compatibility:	Spark NLP 3.4.2+
License:	Open Source
Edition:	Official
Input Labels:	[document, token]
Output Labels:	[ner]
Language:	fa
Size:	607.0 MB
Case sensitive:	true
Max sentence length:	128

References

https://huggingface.co/HooshvareLab/bert-base-parsbert-armanner-uncased
https://arxiv.org/abs/2005.12515
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/

PREVIOUSDutch Named Entity Recognition (from Davlan)

NEXTPersian Named Entity Recognition (from HooshvareLab)