Persian ALBERT Embeddings (from m3hrdadfi)

Description

Pretrained ALBERT Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. albert-fa-base-v2 is a Persian model orginally trained by m3hrdadfi.

Live Demo Open in Colab Download Copy S3 URICopied!

How to use

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

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

embeddings = AlbertEmbeddings.pretrained("albert_embeddings_albert_fa_base_v2","fa") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings")

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

data = spark.createDataFrame([["من عاشق جرقه NLP هستم"]]).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_fa_base_v2","fa") 
.setInputCols(Array("document", "token")) 
.setOutputCol("embeddings")

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

val data = Seq("من عاشق جرقه NLP هستم").toDF("text")

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

import nlu
nlu.load("fa.embed.albert").predict("""من عاشق جرقه NLP هستم""")

Model Information

References

• https://huggingface.co/m3hrdadfi/albert-fa-base-v2
• https://dumps.wikimedia.org/fawiki/
• https://github.com/miras-tech/MirasText
• https://bigbangpage.com/
• https://www.chetor.com/
• https://www.eligasht.com/Blog/
• https://www.digikala.com/mag/
• https://www.ted.com/talks
• https://github.com/m3hrdadfi/albert-persian
• https://github.com/hooshvare/parsbert
• https://github.com/m3hrdadfi/albert-persian