Edit on GitHub
  • John Snow Labs
  • Dec 06, 2022

Swedish BertForMaskedLM Cased model (from Addedk)

  • sv
  • open_source
  • bert_embeddings
  • bertformaskedlm

Description

Pretrained BertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. kbbert-distilled-cased is a Swedish model originally trained by Addedk.

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_kb_distilled_cased","sv") \
    .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_kb_distilled_cased","sv")
    .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("sv.embed.bert.distilled_cased").predict("""I love Spark NLP""")

Model Information

Model Name: bert_embeddings_kb_distilled_cased
Compatibility: Spark NLP 4.2.4+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: sv
Size: 308.3 MB
Case sensitive: true

References

  • https://huggingface.co/Addedk/kbbert-distilled-cased
  • https://spraakbanken.gu.se/en/resources/gigaword
  • https://github.com/AddedK/swedish-mbert-distillation/blob/main/azureML/pretrain_distillation.py
  • https://kth.diva-portal.org/smash/record.jsf?aq2=%5B%5B%5D%5D&c=2&af=%5B%5D&searchType=UNDERGRADUATE&sortOrder2=title_sort_asc&language=en&pid=diva2%3A1698451&aq=%5B%5B%7B%22freeText%22%3A%22added+kina%22%7D%5D%5D&sf=all&aqe=%5B%5D&sortOrder=author_sort_asc&onlyFullText=false&noOfRows=50&dswid=-6142
  • https://arxiv.org/abs/2103.06418
  • https://spraakbanken.gu.se/en/resources/gigaword