Japanese BertForMaskedLM Base Cased model (from cl-tohoku)

Description

Pretrained BertForMaskedLM model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-base-japanese-v2 is a Japanese model originally trained by cl-tohoku.

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_japanese_v2","ja") \
    .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_japanese_v2","ja")
    .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("ja.embed.bert.v2_base.by_cl_tohoku").predict("""I love Spark NLP""")

Model Information

References

• https://huggingface.co/cl-tohoku/bert-base-japanese-v2
• https://github.com/google-research/bert
• https://pypi.org/project/unidic-lite/
• https://github.com/cl-tohoku/bert-japanese/tree/v2.0
• https://taku910.github.io/mecab/
• https://github.com/neologd/mecab-ipadic-neologd
• https://github.com/polm/fugashi
• https://github.com/polm/unidic-lite
• https://www.tensorflow.org/tfrc/
• https://creativecommons.org/licenses/by-sa/3.0/
• https://www.tensorflow.org/tfrc/