English Financial BERT Sentence Embeddings( Finance, 768D)

Description

Pretrained Financial BERT Sentence Embeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. setfit-finetuned-financial-text-classification is a English Financial model which is maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Live Demo Open in Colab Download Copy S3 URI

How to use

sentence_embeddings = BertSentenceEmbeddings.pretrained("sbert_setfit_finetuned_financial_text_classification", "en")\
  .setInputCols(["sentence"])\
  .setOutputCol("sbert_embeddings")

val sentence_embeddings = BertSentenceEmbeddings.pretrained("sbert_setfit_finetuned_financial_text_classification", "en")
  .setInputCols("sentence")
  .setOutputCol("bert_sentence"))

import nlu
nlu.load("en.embed_sentence.bert.finetuned").predict("""Put your text here.""")

Model Information

References

https://huggingface.co/nickmuchi/setfit-finetuned-financial-text-classification