Bangla Bert Embeddings (from monsoon-nlp)


Pretrained Bert Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. muril-adapted-local is a Bangla model orginally trained by monsoon-nlp.


How to use

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

tokenizer = Tokenizer() \
    .setInputCols("document") \
embeddings = BertEmbeddings.pretrained("bert_embeddings_muril_adapted_local","bn") \
    .setInputCols(["document", "token"]) \
pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["আমি স্পার্ক এনএলপি ভালোবাসি"]]).toDF("text")

result =
val documentAssembler = new DocumentAssembler() 
val tokenizer = new Tokenizer() 

val embeddings = BertEmbeddings.pretrained("bert_embeddings_muril_adapted_local","bn") 
    .setInputCols(Array("document", "token")) 

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

val data = Seq("আমি স্পার্ক এনএলপি ভালোবাসি").toDF("text")

val result =
import nlu
nlu.load("bn.embed.muril_adapted_local").predict("""আমি স্পার্ক এনএলপি ভালোবাসি""")

Model Information

Model Name: bert_embeddings_muril_adapted_local
Compatibility: Spark NLP 3.4.2+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: bn
Size: 888.7 MB
Case sensitive: true