This node trains a Doc2Vec (Paragraph Vectors) model on labelled documents. The model will learn sequence representations (vector for each label) as well as word representations (vector for each word), that can be extracted using the Vocabulary Extractor Node. For more information on Word Vectors in general see: http://deeplearning4j.org/word2vec
- Type: Data Table containing Document or String columns.
- Type: Word Vector Model Trained Doc2Vec Model.
KNIME Labs > Deep Learning > DL4J > Word Embeddings
Make sure to have this extension installed: