Chinese Bert Embeddings (from celtics1863)

Description

Pretrained Bert Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. env-bert-chinese is a Chinese model orginally trained by celtics1863.

Download Copy S3 URI

How to use

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

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

embeddings = BertEmbeddings.pretrained("bert_embeddings_env_bert_chinese","zh") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings")

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

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

val embeddings = BertEmbeddings.pretrained("bert_embeddings_env_bert_chinese","zh") 
.setInputCols(Array("document", "token")) 
.setOutputCol("embeddings")

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

val data = Seq("I love Spark NLP").toDF("text")

val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("zh.embed.env_bert_chinese").predict("""I love Spark NLP""")

Model Information

Model Name: bert_embeddings_env_bert_chinese
Compatibility: Spark NLP 3.4.2+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: zh
Size: 384.1 MB
Case sensitive: true

References

  • https://huggingface.co/celtics1863/env-bert-chinese