Portuguese BERT Embeddings (Large Cased)

Description

This is the pre-trained BERT model trained on the Portuguese language. BERT-Base and BERT-Large Cased variants were trained on the BrWaC (Brazilian Web as Corpus), a large Portuguese corpus, for 1,000,000 steps, using whole-word mask.

Download

How to use

...
embeddings = BertEmbeddings.pretrained("bert_portuguese_large_cased", "pt") \
      .setInputCols("sentence", "token") \
      .setOutputCol("embeddings")
nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, tokenizer, embeddings])
pipeline_model = nlp_pipeline.fit(spark.createDataFrame([[""]]).toDF("text"))
result = pipeline_model.transform(spark.createDataFrame(pd.DataFrame({"text": ["Eu amo PNL"]})))
...
val embeddings = BertEmbeddings.pretrained("bert_portuguese_large_cased", "pt")
      .setInputCols("sentence", "token")
      .setOutputCol("embeddings")
val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, tokenizer, embeddings))
val result = pipeline.fit(Seq.empty["Eu amo PNL"].toDS.toDF("text")).transform(data)
import nlu

text = ["Eu amo PNL"]
embeddings_df = nlu.load('pt.bert.cased.large').predict(text, output_level='token')
embeddings_df

Results

	token	pt_bert_cased_large_embeddings
		
      Eu 	[0.6893012523651123, 0.18436528742313385, 0.14...
 	amo 	[0.6536692976951599, 0.17582201957702637, -0.5...
 	PNL 	[-0.1397203803062439, 0.5698696374893188, -0.3...

Model Information

Model Name: bert_portuguese_large_cased
Type: embeddings
Compatibility: Spark NLP 2.6.0+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [word_embeddings]
Language: [pt]
Dimension: 1024
Case sensitive: true

Data Source

The model is imported from https://github.com/neuralmind-ai/portuguese-bert