Edit on GitHub
  • John Snow Labs
  • Nov 15, 2022

Spanish Legal Longformer Embeddings (from Narrativa)

  • longformer
  • es
  • spanish
  • embeddings
  • transformer
  • open_source
  • tensorflow

Description

Pretrained Longformer Embeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. longformer_legal_embeddings is a Spanish model originally trained by Narrative.

Download Copy S3 URI

How to use


 embeddings = LongformerEmbeddings\
.pretrained("longformer_legal_embeddings","es")\
.setInputCols(["document", "token"])\
.setOutputCol("embeddings")



val embeddings = LongformerEmbeddings.pretrained("longformer_legal_embeddings","es")
.setInputCols("document", "token") 
.setOutputCol("embeddings")


import nlu
nlu.load("es.embed.longformer.legal").predict("""Put your text here.""")

Model Information

Model Name: longformer_legal_embeddings
Compatibility: Spark NLP 4.2.0+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [embeddings]
Language: es
Size: 564.1 MB
Case sensitive: true
Max sentence length: 4096

References

https://huggingface.co/Narrativa/legal-longformer-base-4096-spanish