German BertForSequenceClassification Cased model (from inovex)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. multi2convai-logistics-de-bert is a German model originally trained by inovex.

Predicted Entities

navigate, tour.job.delivered, safeplace, no, details.preferedNeighbour, undefined, yes, help, select, details.safeplace, details.avoidNeighbour, tour.start, tour.postcode.select, tour.job.safePlace, navigate.back, tour.details, tour.job.collected, tour.finish, tour.job.failed, tour.job.carriedForward, tour.job.signature, details.address

Download Copy S3 URI

How to use

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

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

sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_multi2convai_logistics_de_bert","de") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

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

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 sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_multi2convai_logistics_de_bert","de")
    .setInputCols(Array("document", "token"))
    .setOutputCol("ner")

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

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

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

Model Information

Model Name:	bert_sequence_classifier_multi2convai_logistics_de_bert
Compatibility:	Spark NLP 4.3.1+
License:	Open Source
Edition:	Official
Input Labels:	[document, token]
Output Labels:	[ner]
Language:	de
Size:	412.8 MB
Case sensitive:	true
Max sentence length:	128

References

https://huggingface.co/inovex/multi2convai-logistics-de-bert
https://multi2conv.ai
https://multi2convai/en/blog/use-cases
https://multi2convai/en/blog/use-cases
https://multi2conv.ai
https://github.com/inovex/multi2convai

PREVIOUSItalian BertForSequenceClassification Cased model (from inovex)

NEXTEnglish BertForSequenceClassification Cased model (from inovex)