Word Vector Apply


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.

Input Ports

  1. Type: Data Table containing Document or String Column.
  2. Type: Word Vector Model The Word Vector Model to use for word vector lookup.

Output Ports

  1. Type: Data Table with list of word vectors or single mean word vector.

Find here

KNIME Labs > Deep Learning > DL4J > Word Embeddings

Make sure to have this extension installed:

KNIME Textprocessing - Deeplearning4J Integration (64bit only)

Update site for KNIME Analytics Platform 3.7:
KNIME Analytics Platform 3.7 Update Site

How to install extensions