Italian Part of Speech Tagger (from sachaarbonel)

Description

Pretrained Part of Speech model model, uploaded to Hugging Face, adapted and imported into Spark NLP. bert-italian-cased-finetuned-pos is a Italian model orginally trained by sachaarbonel.

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_pos_bert_italian_cased_finetuned_pos","it") \
    .setInputCols(["sentence", "token"]) \
    .setOutputCol("pos")

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

data = spark.createDataFrame([["Adoro 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_pos_bert_italian_cased_finetuned_pos","it") 
    .setInputCols(Array("sentence", "token")) 
    .setOutputCol("pos")

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

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

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

import nlu
nlu.load("it.ner.pos.xtreme.cased_finetuned").predict("""Adoro Spark NLP""")

Model Information

Model Name:	bert_pos_bert_italian_cased_finetuned_pos
Compatibility:	Spark NLP 3.4.2+
License:	Open Source
Edition:	Official
Input Labels:	[document, token]
Output Labels:	[ner]
Language:	it
Size:	410.3 MB
Case sensitive:	true
Max sentence length:	128

References

https://huggingface.co/sachaarbonel/bert-italian-cased-finetuned-pos
https://raw.githubusercontent.com/stefan-it/fine-tuned-berts-seq/master/scripts/preprocess.py
https://twitter.com/sachaarbonel
https://www.linkedin.com/in/sacha-arbonel

PREVIOUSThai Part of Speech Tagger (from KoichiYasuoka)

NEXTGerman Part of Speech Tagger (from KoichiYasuoka)