IBM Cloud Docs
Using the machine learning model

Using the machine learning model

Leverage a machine learning model that you trained with Knowledge Studio for IBM Cloud Pak for Data by making it available to other Watson applications.

You can deploy or export a machine learning model. A dictionary can only be used to pre-annotate documents within Knowledge Studio.

You can also pre-annotate new documents with the machine learning model. See Pre-annotating documents with the machine learning model for details.

Exporting a machine learning model

To export a machine learning model as a .zip file, complete the following steps:

  1. Log in as a Knowledge Studio administrator or project manager, and select your workspace.

  2. Select Machine Learning Model > Versions.

  3. Choose the version of the model that you want to export, or select Export current model.

    If there is only one working version of the model, create a snapshot of the current model. This versions the model, which enables you to deploy one version, while you continue to improve the current version. The option to deploy does not appear until you create at least one version.

  4. Click Export, and then click Export again to confirm.

Deploying a machine learning model to IBM Watson Discovery for IBM Cloud Pak for Data

When you are satisfied with the performance of the model, you can export a version to IBM Watson® Discovery for IBM Cloud Pak for Data. This feature enables your applications to use the deployed machine learning model to enrich the insights that you get from your data to include the recognition of entities and relations that are relevant to your domain.

Before you begin

You must have administrative access to a Discovery for IBM Cloud Pak for Data deployment.

Procedure

  1. Export a machine learning model.
  2. To use the deployed model, you must upload it when it is requested during the Discovery service enrichment configuration process. For more information, see the Discovery documentation.

Deploying a machine learning model to IBM Watson Natural Language Understanding for IBM Cloud Pak for Data

When you are satisfied with the performance of the model, you can deploy a version of it to IBM Watson Natural Language Understanding. This feature enables your applications to use the deployed machine learning model to analyze custom entities and relations.

Before you begin

You must have a Natural Language Understanding for IBM Cloud Pak for Data deployment.

Procedure

  1. Export a machine learning model.
  2. Follow the Customizing instructions in the Natural Language Understanding for IBM Cloud Pak for Data documentation to create an entities model with the .zip file that you downloaded.

Deleting a version

If you wish to delete a specific version a same machine learning model, navigate to the Versions page and click the Delete link on the row of the version that you want to delete. Note: The Delete model version link is only active if there are no deployed models associated with it. Undeploy all associated models before deleting the a version.

Leveraging a machine learning model in IBM Watson Explorer

Export the trained machine learning model so it can be used in IBM Watson Explorer.

Before you begin

If you choose to identify relation types and annotate them, then you must define at least two relation types, and annotate instances of the relationships in the ground truth before you export the model. Defining and annotating only one relation type can cause subsequent issues in IBM Watson Explorer, release 11.0.1.0.

About this task

Now that the machine learning model is trained to recognize entities and relationships for a specific domain, you can leverage it in IBM Watson Explorer.

Watch a less than 2-minute video that illustrates how to export a model and use it in IBM Watson Explorer.

Procedure

  1. Export a machine learning model.

  2. From the IBM Watson Explorer application, import the model.

    You can then map the model to a machine learning model in Watson Explorer Content Analytics. After you perform the mapping step, when you crawl documents, the model finds instances of the entities and relations that your model understands. To learn how to import and configure the model in IBM Watson Explorer, see the technical document that describes the integration: http://www.ibm.com/support/docview.wss?uid=swg27048147.