Hub
WorkflowWorkflow

Weak Supervision for Document Classification

Human-in-the-loop Guided analytics Document classification Sentiment analysis Movie reviews
+7

Last edited: 

Drag & drop
Like
Download workflow
Copy short link
Workflow preview
This workflow defines a fully automated web based application that will label your data using weak supervision. The workflow was designed for business analysts to easily go through documents to be labeled in any number of classes. The user provides euristhics, that is simple labeling functions. Some documents gets labeled, a generative model is applied, and a model can be trained using the a probabilistic input. Gradient Boosted Trees was used after the Weak Label. This workflow is made to be deployed on KNIME WebPortal via KNIME Server.

Used extensions & nodes

Created with KNIME Analytics Platform version 4.5.1
  • KNIME Base nodes Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.1

  • KNIME Data Generation Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.0

  • KNIME Ensemble Learning Wrappers Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.0

  • KNIME Expressions Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.1

  • KNIME JavaScript Views Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.1

  • KNIME Javasnippet Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.0

  • KNIME Machine Learning Interpretability Extension Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.0

  • KNIME Math Expression (JEP) Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.0

  • KNIME Quick Forms Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.0

  • KNIME Textprocessing Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.0

  • KNIME Weak Supervision Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.5.0

Discussion