Chinese BertForSequenceClassification Cased model (from Ayazhankad)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. bert-finetuned-semantic-chinese is a Chinese model originally trained by Ayazhankad.

Predicted Entities

Star_1, Star_2, Star_3, Star_4, Star_5

Live Demo Open in Colab Download Copy S3 URI

How to use

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

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

sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_finetuned_semantic_chinese","zh") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

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

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(Array("document"))
    .setOutputCol("token")

val sequenceClassifier_loaded = BertForSequenceClassification.pretrained("bert_classifier_finetuned_semantic_chinese","zh") 
    .setInputCols(Array("document", "token")) 
    .setOutputCol("class")

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

val data = Seq("PUT YOUR STRING HERE").toDF("text")

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

import nlu
nlu.load("zh.classify.bert.finetuned").predict("""PUT YOUR STRING HERE""")

Model Information

References

• https://huggingface.co/Ayazhankad/bert-finetuned-semantic-chinese
• https://www.kaggle.com/datasets/utmhikari/doubanmovieshortcomments
• https://www.kaggle.com
• https://en.wikipedia.org/wiki/Douban#:~:text=Douban.com%20(Chinese%3A%20%E8%B1%86%E7%93%A3,and%20activities%20in%20Chinese%20cities.
• https://www.kaggle.com/datasets/utmhikari/doubanmovieshortcomments
• https://www.kaggle.com