Arabic Bert Embeddings (Base, Trained on a sixteenth of the full MSA dataset)

Description

Pretrained Bert Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. bert-base-arabic-camelbert-msa-sixteenth is a Arabic model orginally trained by CAMeL-Lab.

Download

How to use

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

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

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

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

data = spark.createDataFrame([["أنا أحب شرارة 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_bert_base_arabic_camelbert_msa_sixteenth","ar") 
.setInputCols(Array("document", "token")) 
.setOutputCol("embeddings")

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

val data = Seq("أنا أحب شرارة NLP").toDF("text")

val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("ar.embed.bert_base_arabic_camelbert_msa_sixteenth").predict("""أنا أحب شرارة NLP""")

Model Information

Model Name: bert_embeddings_bert_base_arabic_camelbert_msa_sixteenth
Compatibility: Spark NLP 3.4.2+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: ar
Size: 409.3 MB
Case sensitive: true

References

  • https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-msa-sixteenth
  • https://arxiv.org/abs/2103.06678
  • https://github.com/CAMeL-Lab/CAMeLBERT
  • https://catalog.ldc.upenn.edu/LDC2011T11
  • http://www.abuelkhair.net/index.php/en/arabic/abu-el-khair-corpus
  • https://vlo.clarin.eu/search;jsessionid=31066390B2C9E8C6304845BA79869AC1?1&q=osian
  • https://archive.org/details/arwiki-20190201
  • https://oscar-corpus.com/
  • https://github.com/google-research/bert
  • https://github.com/google-research/bert/blob/eedf5716ce1268e56f0a50264a88cafad334ac61/tokenization.py#L286-L297
  • https://github.com/CAMeL-Lab/camel_tools
  • https://github.com/CAMeL-Lab/CAMeLBERT