Financial English Bert Embeddings (Base, Communication texts)

Description

Financial English Bert Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. finbert-pretrain-yiyanghkust is a English model orginally available in Hugging Face as yiyanghkust/finbert-pretrain. It was trained on the following datasets:

  • Corporate Reports 10-K & 10-Q: 2.5B tokens
  • Earnings Call Transcripts: 1.3B tokens
  • Analyst Reports: 1.1B tokens

Download

How to use

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

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")
  
embeddings = BertEmbeddings.pretrained("bert_embeddings_finbert_pretrain_yiyanghkust","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_finbert_pretrain_yiyanghkust","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)

Model Information

Model Name: bert_embeddings_finbert_pretrain_yiyanghkust
Compatibility: Spark NLP 3.4.2+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: en
Size: 412.3 MB
Case sensitive: true

References

  • https://huggingface.co/philschmid/finbert-pretrain-yiyanghkust
  • https://arxiv.org/abs/2006.08097