French CamemBert Embeddings (from HueyNemud)

Description

Pretrained CamemBert Embeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. das22-10-camembert_pretrained is a French model orginally trained by HueyNemud.

Download Copy S3 URI

How to use

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

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")
  
embeddings = CamemBertEmbeddings.pretrained("camembert_embeddings_das22_10_camembert_pretrained","fr") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("embeddings")
    
pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["J'adore 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 = CamemBertEmbeddings.pretrained("camembert_embeddings_das22_10_camembert_pretrained","fr") 
    .setInputCols(Array("document", "token")) 
    .setOutputCol("embeddings")

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

val data = Seq("J'adore Spark NLP").toDF("text")

val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("fr.embed.camembert.by_hueynemud").predict("""J'adore Spark NLP""")

Model Information

Model Name: camembert_embeddings_das22_10_camembert_pretrained
Compatibility: Spark NLP 3.4.4+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [embeddings]
Language: fr
Size: 415.7 MB
Case sensitive: true

References

  • https://huggingface.co/HueyNemud/das22-10-camembert_pretrained
  • https://doi.org/10.1007/978-3-031-06555-2_30
  • https://github.com/soduco/paper-ner-bench-das22