Description
Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
Predicted Entities
How to use
embeddings =E5Embeddings.pretrained("e5_base_v2_opt","en") \
            .setInputCols(["documents"]) \
            .setOutputCol("instructor")
pipeline = Pipeline().setStages([document_assembler, embeddings])
val embeddings = E5Embeddings.pretrained("e5_base_v2_opt","en")
      .setInputCols(["document"])
      .setOutputCol("e5_embeddings")
val pipeline = new Pipeline().setStages(Array(document, embeddings))
Model Information
| Model Name: | e5_base_v2_opt | 
| Compatibility: | Spark NLP 5.1.0+ | 
| License: | Open Source | 
| Edition: | Official | 
| Input Labels: | [documents] | 
| Output Labels: | [e5] | 
| Language: | en | 
| Size: | 258.8 MB |