Chinese BertForSequenceClassification Cased model (from IDEA-CCNL)

Description

Pretrained BertForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. Erlangshen-Roberta-330M-NLI is a Chinese model originally trained by IDEA-CCNL.

Predicted Entities

ENTAILMENT, NEUTRAL, CONTRADICTION

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 = BertForSequenceClassification.pretrained("bert_sequence_classifier_erlangshen_roberta_330m_nli","zh") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

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

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 sequenceClassifier = BertForSequenceClassification.pretrained("bert_sequence_classifier_erlangshen_roberta_330m_nli","zh")
    .setInputCols(Array("document", "token"))
    .setOutputCol("ner")

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

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

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

Model Information

References

• https://huggingface.co/IDEA-CCNL/Erlangshen-Roberta-330M-NLI
• https://github.com/IDEA-CCNL/Fengshenbang-LM
• https://fengshenbang-doc.readthedocs.io/
• https://arxiv.org/abs/2209.02970
• https://arxiv.org/abs/2209.02970
• https://github.com/IDEA-CCNL/Fengshenbang-LM/
• https://github.com/IDEA-CCNL/Fengshenbang-LM/