Description
Word Embeddings lookup annotator that maps tokens to vectors.
How to use
model = WordEmbeddingsModel.pretrained("embeddings_scielowiki_50d","es","clinical/models")\
.setInputCols(["document","token"])\
.setOutputCol("word_embeddings")
val model = WordEmbeddingsModel.pretrained("embeddings_scielowiki_50d","es","clinical/models")
.setInputCols("document","token")
.setOutputCol("word_embeddings")
import nlu
nlu.load("es.embed.scielowiki.50d").predict("""Put your text here.""")
Results
Word2Vec feature vectors based on embeddings_scielowiki_50d.
Model Information
| Name: | embeddings_scielowiki_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 Scielo Articles + Clinical Wikipedia Articles https://zenodo.org/record/3744326#.XtViinVKh_U