Skip to content

Make experiments in extraction projects

Overview

Once annotations have been created for all defined information classes, you can perform experiments which consist of creating the extraction ML model.

Annotate provides the following model types for extraction projects:

The first one creates a Machine Learning model, while the second one a model based on an expert.ai Studio CPK of an imported project.

To start an experiment:

  1. Select Start an experiment to pre-annotate documents on the toolbar of the project dashboard.
    The experiment wizard starts.

  2. In the Start an experiment dialog:

    2.1. Enter the experiment name in Name or leave empty for automatic assignment.

    2.2. Select the test library in the Test library drop-down menu.

    2.3. Select the available engine type:

    • Auto-ML Extraction

    or:

    • Studio

    2.4. Select Start or Next if you selected Studio.

The experiment progress window is displayed during the engine process.

To terminate the process before its end, select Delete experiment.

The process consists of six sequential stages:

  1. Initialization
  2. Model generation preparation
  3. Model generation
  4. Document analysis preparation
  5. Document analysis
  6. Experiment wrap-up

Once the process is completed, the analytics are displayed in the Experiments tab, Statistics sub-tab where it is possible to interpret the results.

Studio engine procedure

  1. Select the model in Model selection, then select Next to go on.
  2. Check the remap in Remapper then select Next to go on.
  3. Check the summary and select Start.