Financial English BERT Embeddings (Base)

Description

Financial Pretrained BERT Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. sec-bert-base is a English model orginally trained by nlpaueb. This is the reference base model, what means it uses the same architecture as BERT-BASE trained on financial documents.

If you are interested in Financial Embeddings, take a look also at these two models:

• sec-num: Same as this base model but we replace every number token with a [NUM] pseudo-token handling all numeric expressions in a uniform manner, disallowing their fragmentation).
• sec-shape: Same as this base model but we replace numbers with pseudo-tokens that represent the number’s shape, so numeric expressions (of known shapes) are no longer fragmented, e.g., ‘53.2’ becomes ‘[XX.X]’ and ‘40,200.5’ becomes ‘[XX,XXX.X]’.

Live Demo Open in Colab Download Copy S3 URI

How to use

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

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

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

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

data = spark.createDataFrame([["I love 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 = BertEmbeddings.pretrained("bert_embeddings_sec_bert_base","en") 
.setInputCols(Array("document", "token")) 
.setOutputCol("embeddings")

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

val data = Seq("I love Spark NLP").toDF("text")

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

import nlu
nlu.load("en.embed.sec_bert_base").predict("""I love Spark NLP""")

Model Information

References

• https://huggingface.co/nlpaueb/sec-bert-base
• https://arxiv.org/abs/2203.06482
• http://nlp.cs.aueb.gr/