Malay ALBERT Embeddings (from malay-huggingface)

Description

Pretrained ALBERT Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. albert-tiny-bahasa-cased is a Malay model orginally trained by malay-huggingface.

Download

How to use

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

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")
  
embeddings = AlbertEmbeddings.pretrained("albert_embeddings_albert_tiny_bahasa_cased","ms") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("embeddings")
    
pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["Saya suka 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 = AlbertEmbeddings.pretrained("albert_embeddings_albert_tiny_bahasa_cased","ms") 
    .setInputCols(Array("document", "token")) 
    .setOutputCol("embeddings")

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

val data = Seq("Saya suka Spark NLP").toDF("text")

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

Model Information

Model Name: albert_embeddings_albert_tiny_bahasa_cased
Compatibility: Spark NLP 3.4.2+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: ms
Size: 21.9 MB
Case sensitive: false

References

  • https://huggingface.co/malay-huggingface/albert-tiny-bahasa-cased
  • https://github.com/huseinzol05/malay-dataset/tree/master/dumping/clean
  • https://github.com/huseinzol05/malay-dataset/tree/master/corpus/pile
  • https://github.com/huseinzol05/Malaya/tree/master/pretrained-model/albert