Embeddings Sciwiki 50 dims

Description

Word Embeddings lookup annotator that maps tokens to vectors.

Copy S3 URI

How to use

model = WordEmbeddingsModel.pretrained("embeddings_sciwiki_50d","es","clinical/models")\
	.setInputCols(["document","token"])\
	.setOutputCol("word_embeddings")
val model = WordEmbeddingsModel.pretrained("embeddings_sciwiki_50d","es","clinical/models")
	.setInputCols("document","token")
	.setOutputCol("word_embeddings")
import nlu
nlu.load("es.embed.sciwiki.50d").predict("""Put your text here.""")

Results

Word2Vec feature vectors based on embeddings_sciwiki_50d.

Model Information

Name: embeddings_sciwiki_50d
Type: WordEmbeddingsModel
Compatibility: Spark NLP 2.5.0+
License: Licensed
Edition: Official
Input labels: [document, token]
Output labels: [word_embeddings]
Language: es
Dimension: 50.0

Data Source

Trained on Clinical Wikipedia Articles https://zenodo.org/record/3744326#.XtViinVKh_U