English BertForTokenClassification Base Cased model (from Jzuluaga)

Description

Pretrained BertForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-base-ner-atc-en-atco2-1h is a English model originally trained by Jzuluaga.

Predicted Entities

command, value, callsign, O

Download Copy S3 URI

How to use

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

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

tokenClassifier = BertForTokenClassification.pretrained("bert_token_classifier_base_ner_atc_en_atco2_1h","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("ner")

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

data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")

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

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

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

val tokenClassifier = BertForTokenClassification.pretrained("bert_token_classifier_base_ner_atc_en_atco2_1h","en")
    .setInputCols(Array("document", "token"))
    .setOutputCol("ner")

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

val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")

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

Model Information

Model Name:	bert_token_classifier_base_ner_atc_en_atco2_1h
Compatibility:	Spark NLP 4.3.1+
License:	Open Source
Edition:	Official
Input Labels:	[document, token]
Output Labels:	[ner]
Language:	en
Size:	407.8 MB
Case sensitive:	true
Max sentence length:	128

References

https://huggingface.co/Jzuluaga/bert-base-ner-atc-en-atco2-1h
https://github.com/idiap/atco2-corpus
https://arxiv.org/abs/2211.04054
https://www.atco2.org/data
https://github.com/idiap/atco2-corpus
https://arxiv.org/abs/2211.04054
https://www.atco2.org/data
https://github.com/idiap/atco2-corpus/tree/main/data/databases/atco2_test_set_1h/data_prepare_atco2_corpus_other.sh
https://paperswithcode.com/sota?task=ner&dataset=ATCO2+corpus+%28Air+Traffic+Control+Communications%29

PREVIOUSNorwegian BertForTokenClassification Base Cased model (from Kushtrim)

NEXTSwedish BertForTokenClassification Base Cased model (from KBLab)