German BertForTokenClassification Cased model (from elenanereiss)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-german-ler is a German model originally trained by elenanereiss.

Predicted Entities

``, EUN, LIT, RR, INN, RS, PER, VO, UN, MRK, AN, LD, STR, GRT, ORG, GS, VT, LDS, ST, VS

Live Demo Open in Colab 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_german_ler","de") \
    .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_german_ler","de")
    .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)

import nlu
nlu.load("de.ner.bert.by_elenanereiss").predict("""PUT YOUR STRING HERE""")

Model Information

References

• https://huggingface.co/elenanereiss/bert-german-ler
• https://github.com/elenanereiss/bert-legal-ner
• https://paperswithcode.com/sota?task=Token+Classification&dataset=elenanereiss%2Fgerman-ler