Skip to content

Manage models

Overview

Models are the text analysis engines produced by either running experiments or importing CPK files.

To access the list of all the models generated for the project or the imported ones, select the Models tab.

The models marked with a green dot in the Published column are those that have been published, i.e. made available for inclusion in workflows.

To publish and unpublish, the procedure is the same described in the model features page.

Sort the list

To sort the list, select a column header.

Filter the list

To filter the model list according its type, select Engine, then the model type.

To filter the model list according the train library, select Train library, then the library.

Change a model name

To change a model name, select Edit model name on the toolbar of the right panel.

Delete a model

To delete a model name, select Delete model on the toolbar of the right panel.

Export a model

To export a model:

  1. Select Export model if the model is generated with an Auto-ML Extraction engine or Export CPK if uploaded.
  2. In the Export model window (or Export CPK window), type the model name in File name or confirm the suggested one, then select:

    • Export model

    Or:

    • Export CPK (in case of a CPK)
  3. Select Download either in the dialog or in the notification in the lower right corner.

Upload a CPK

Select Upload CPK to upload a CPK.

Start an experiment

To start a new experiment:

  1. Select a model in the models list, then select Quick start an experiment.
  2. In the dialog, enter the experiment name in Name or confirm the suggested one, select the test library in Test library, then select Next.
  3. Check the summary, select the match strategy from the Metrics Matching Strategy drop-down menu, then select Start.

Create a Knowledge Graph Customization project

To create a Knowledge Graph Customization project:

  1. Select a CPK from the list of available models.
  2. Select Knowledge Graph Customization.

  3. In the dialog, type a name, an optional description and select Create.

Note

The creation procedure will occur as a background task.

Publish and unpublish a model

The models marked with a green dot in the Published column are those that have been published, that is made available for inclusion in workflows.

To publish a model, select it from the list then select Publish model on the right panel.

Note

If you publish a generated model—not an imported CPK—you will be asked to confirm or change the model name.

To unpublish a model, select Unpublish model on the right panel.

See the general or the training settings

Select the General or the Train settings sub-tabs in the Model Details panel to see the general training settings,

Resources (Available for Auto-ML extraction experiment type only)

Select the Resources sub-panel, in the Model Details panel to see detailed information about the extraction classes. Available for Auto-ML extraction experiment type only.

You can check a related experiment in the Related experiments sub-panel, by double-clicking it. You will see the experiment quality.

Remapping

Since the imported CPK model may differ from the project you are working on, for example because it is produced at different times or by different users, it is sometimes necessary to remap it.

Select Remap CPK if you need to remap the resources (classes and groups in the extraction projects) between the CPK imported model and the existing project.

The remap view is displayed and the focus is on the imported CPK model resources.

The remap view is divided into two panels:

  • The left one shows the imported Model Information and the existing Project resources.

  • The right one shows four tabs that help you in the resources remapping.

All resources

This tab shows the complete resources of the imported model and if and how they have been remapped.

If no automatic remapping occurred, no match will be shown. Therefore it will be possible to perform a manual remapping, if it is considered appropriate.

If you want to manually remap a resource from the imported model to a class of the existing project:

  1. Select a class, or a class that belongs to a group, from the list box on the right side.
  2. Select Save to confirm.

This remapping will be displayed in the Remapped tab.

Remapped

This tab shows the remapped items, both manually and automatically.

Missed

This tab shows the imported model resources that don't have a mapping with the existing model resources.

If you want to remap a resource from the imported model to a class of the existing project:

  1. Select a class, or a class that belongs to a group, from the list box at the right side.
  2. Select Save to confirm.

This mapping will be displayed in the Remapped tab.

Not Mapped

This tab shows the existing resources that don't have any mapping with the imported resources.