Chinese BertForTokenClassification Cased model (from canIjoin)

Description

Pretrained BertForTokenClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. datafun is a Chinese model originally trained by canIjoin.

Predicted Entities

movie, no1, government, name1, position, book1, address, address1, game, organization, book, government1, company1, game1, position1, movie1, scene1, name, company, scene, organization1

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_datafun","zh") \
    .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_datafun","zh")
    .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)

Model Information

References

• https://huggingface.co/canIjoin/datafun
• https://github.com/dbiir/UER-py/wiki/Modelzoo
• https://github.com/CLUEbenchmark/CLUENER2020
• https://github.com/dbiir/UER-py/
• https://cloud.tencent.com/