This node applies a Word Vector Model to Documents or Strings, meaning that every word contained in the text (tokenized by whitespace) will be replaced by the corresponding Word Vector if the word is available in the Word Vector dictionary. This will result in a list of Word Vectors. If specified, the node calculates the mean of these vectors resulting in a single representation of the input.
The KNIME Deeplearning4J Integration has been marked as legacy with KNIME Analytics Platform 5.0 and will be deprecated in a future version. If you are using this extension in a production workflow, consider switching to one of the other deep learning integrations available in KNIME Analytics Platform.