Finnish BertForMaskedLM Base Cased model (from TurkuNLP)

Description

Pretrained BertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-base-finnish-cased-v1 is a Finnish model originally trained by TurkuNLP.

Live Demo Open in Colab 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_base_finnish_cased_v1","fi") \
    .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_base_finnish_cased_v1","fi")
    .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("fi.embed.bert.cased_base").predict("""I love Spark NLP""")

Model Information

References

• https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1
• https://arxiv.org/abs/1912.07076
• https://github.com/google-research/bert
• https://github.com/google-research/bert/blob/master/multilingual.md
• https://raw.githubusercontent.com/TurkuNLP/FinBERT/master/img/yle-ylilauta-curves.png
• https://fasttext.cc/
• https://github.com/spyysalo/finbert-text-classification
• https://github.com/spyysalo/yle-corpus
• https://github.com/spyysalo/ylilauta-corpus
• https://arxiv.org/abs/1908.04212
• https://github.com/Traubert/FiNer-rules
• https://arxiv.org/pdf/1908.04212.pdf
• https://github.com/jouniluoma/keras-bert-ner
• https://github.com/mpsilfve/finer-data
• https://universaldependencies.org/
• https://github.com/spyysalo/bert-pos
• http://hdl.handle.net/11234/1-2837
• http://dl.turkunlp.org/finbert/bert-base-finnish-uncased.zip
• http://dl.turkunlp.org/finbert/bert-base-finnish-cased.zip