English Bert Embeddings (from GroNLP)

Description

Pretrained Bert Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. hateBERT is a English model orginally trained by GroNLP.

Download

How to use

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

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")
  
embeddings = BertEmbeddings.pretrained("bert_embeddings_hateBERT","en") \
    .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_hateBERT","en") 
    .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)

Model Information

Model Name: bert_embeddings_hateBERT
Compatibility: Spark NLP 3.4.2+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: en
Size: 409.0 MB
Case sensitive: true

References

  • https://huggingface.co/GroNLP/hateBERT
  • https://www.semanticscholar.org/author/Tommaso-Caselli/1864635
  • https://www.semanticscholar.org/author/Valerio-Basile/3101511
  • https://www.semanticscholar.org/author/Jelena-Mitrovic/145157863
  • https://www.semanticscholar.org/author/M.-Granitzer/2389675
  • https://aclanthology.org/2021.woah-1.3/
  • https://osf.io/tbd58/?view_onlycb79b3228d4248ddb875eb1803525ad8