Description
Word Embeddings lookup annotator that maps tokens to vectors.
Predicted Entities
Open in Colab Download Copy S3 URI
How to use
model = WordEmbeddingsModel.pretrained("w2v_cc_300d","de")\
.setInputCols(["document","token"])\
.setOutputCol("word_embeddings")
val model = WordEmbeddingsModel.pretrained("w2v_cc_300d","de")
.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
| Model Name: | w2v_cc_300d |
| Type: | embeddings |
| Compatibility: | Spark NLP 2.5.5+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [embeddings] |
| Language: | de |
| Size: | 1.2 GB |
| Case sensitive: | false |
| Dimension: | 300 |
References
FastText common crawl word embeddings for Germany https://fasttext.cc/docs/en/crawl-vectors.html