Edit on GitHub
  • John Snow Labs
  • Dec 02, 2022

German BertForMaskedLM Large Cased model (from deepset)

  • de
  • open_source
  • bert_embeddings
  • bertformaskedlm

Description

Pretrained BertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. gbert-large is a German model originally trained by deepset.

Download Copy S3 URI

How to use

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

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

bert_loaded = BertEmbeddings.pretrained("bert_embeddings_g_large","de") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("embeddings") \
    .setCaseSensitive(True)

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

data = spark.createDataFrame([["I love Spark NLP"]]).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 bert_loaded = BertEmbeddings.pretrained("bert_embeddings_g_large","de")
    .setInputCols(Array("document", "token"))
    .setOutputCol("embeddings")
    .setCaseSensitive(True)

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

val data = Seq("I love Spark NLP").toDS.toDF("text")

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

import nlu
nlu.load("de.embed.bert.large").predict("""I love Spark NLP""")

Model Information

Model Name: bert_embeddings_g_large
Compatibility: Spark NLP 4.2.4+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: de
Size: 1.3 GB
Case sensitive: true

References

  • https://huggingface.co/deepset/gbert-large
  • https://arxiv.org/pdf/2010.10906.pdf
  • https://arxiv.org/pdf/2010.10906.pdf
  • http://deepset.ai/
  • https://haystack.deepset.ai/
  • https://deepset.ai/german-bert
  • https://deepset.ai/germanquad
  • https://github.com/deepset-ai/haystack
  • https://docs.haystack.deepset.ai
  • https://haystack.deepset.ai/community
  • https://twitter.com/deepset_ai
  • https://www.linkedin.com/company/deepset-ai/
  • https://haystack.deepset.ai/community
  • https://github.com/deepset-ai/haystack/discussions
  • https://deepset.ai
  • http://www.deepset.ai/jobs