Word Embeddings for French (word2vec_wac_200)

Description

This French Word2Vec model was trained by Jean-Philippe Fauconnier on the frWaC Corpus over a window size of 100 and dimensions of 200.

Predicted Entities

Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")

tokenizer = Tokenizer()\
.setInputCols("document")\
.setOutputCol("token")

embeddings = WordEmbeddingsModel.pretrained("word2vec_wac_200", "fr")\
.setInputCols(["document", "token"])\
.setOutputCol("embeddings")
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")

val tokenizer = new Tokenizer()
.setInputCols("document")
.setOutputCol("token")

val embeddings = WordEmbeddingsModel.pretrained("word2vec_wac_200", "fr")
.setInputCols("document", "token")
.setOutputCol("embeddings")
import nlu
nlu.load("fr.embed.word2vec_wac_200").predict("""Put your text here.""")

Model Information

Model Name: word2vec_wac_200
Type: embeddings
Compatibility: Spark NLP 3.4.0+
License: Open Source
Edition: Official
Input Labels: [document, token]
Output Labels: [embeddings]
Language: fr
Size: 118.0 MB
Case sensitive: false
Dimension: 200

References

This model was trained by Jean-Philippe Fauconnier on the frWaC Corpus. [1]

[1] Fauconnier, Jean-Philippe (2015), French Word Embeddings, http://fauconnier.github.io