0 ×

Word Vector Apply

StreamableKNIME Deeplearning4J Integration Textprocessing version 4.1.0.v201911110939 by KNIME AG, Zurich, Switzerland

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.

Options

Text Column
The column containing the text where the Word Vector Model should be applied to. The text will we tokenized by whitespace. Depending on the type of the input the node will use the following as input:
  • String: the String will be directly used
  • Document: The Document Full Text will be appended to the Document Title separated by a whitespace.
    E.g. a Document with Title: 'Doc A' and Full Text: 'This is a test'
    will result in the following text: 'Doc A This is a test'
Calculate Mean Vector?
Whether to calculate the mean of the word vectors.

Input Ports

Table containing Document or String Column.
The Word Vector Model to use for word vector lookup.

Output Ports

Table with list of word vectors or single mean word vector.

Best Friends (Incoming)

Best Friends (Outgoing)

Workflows

Installation

To use this node in KNIME, install KNIME Textprocessing - Deeplearning4J Integration (64bit only) from the following update site:

KNIME 4.1
Wait a sec! You want to explore and install nodes even faster? We highly recommend our NodePit for KNIME extension for your KNIME Analytics Platform.

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.