Description
Word Embeddings lookup annotator that maps tokens to vectors.
How to use
model = WordEmbeddingsModel.pretrained("w2v_cc_300d","de","clinical/models")\
.setInputCols(["document","token"])\
.setOutputCol("word_embeddings")
val model = WordEmbeddingsModel.pretrained("w2v_cc_300d","de","clinical/models")
.setInputCols(Array("document","token"))
.setOutputCol("word_embeddings")
import nlu
nlu.load("de.embed.w2v").predict("""Put your text here.""")
Results
Word2Vec feature vectors based on w2v_cc_300d.
Model Information
| Name: | w2v_cc_300d |
| Type: | WordEmbeddingsModel |
| Compatibility: | Healthcare NLP 2.5.5+ |
| License: | Licensed |
| Edition: | Official |
| Input labels: | [document, token] |
| Output labels: | [word_embeddings] |
| Language: | de |
| Dimension: | 300.0 |
Data Source
FastText common crawl word embeddings for Germany https://fasttext.cc/docs/en/crawl-vectors.html