Record Categorizations

To review record categorization assignments, navigate to the "Categorizations" page of a Categorization project.

1. Select 1 or more records.
2. Click Verify and choose Tamr or Expert Suggestion

OR

1. Select a single record.
2. On top right-hand-side, click the pop-out tab.
3. Click Details.
4. Choose a categorization.

The first approach is best for bulk accepting suggested categories. The second is best for investigating conflicting responses between Tamr and experts or among experts.

Verifying Categorizations

If Tamr and Reviewers have differing opinions, curators can choose which suggestion to accept. The Verify button provides this functionality, and can be used for 1 or more selected records at a time. The Top Expert Suggestion will accept the expert categorization with the most upvotes, while the Tamr Suggestion will accept Tamr's categorization. In the event of a tie between experts, the categorization will be left unverified.

Resolving Conflicting Responses

If there are conflicting categorizations, the curator has the power to choose which one is accepted.

This is indicated by the green checkmark. If a curator wishes to switch which category is accepted, they can click on the gray circle next to the category. Once a categorization is verified, it will be included in Tamr's machine learning model.

Clearing Categorizations

Clearing a record categorization

To clear a record user-categorization:

1. Navigate to the Categorizations page of a Classification Project.
2. Select a record.
3. On top right-hand-side, click the pop-out tab and click Details.
4. Click New Categorization -> Clear Categorization.

Clearing all categorizations for a single category

📘

Clearing user-categorizations for a selected category, clears categorizations for all of its descendants.

To clear all record user-categorizations for a selected category:

1. Navigate to the Categories page of a Classification Project.
2. Select a category.
3. Click on the three vertical dots icon in the upper right.
4. Click Clear Categorizations.

Applying Feedback and Updating Categorization Results

📘

Apply Feedback and Update Results

The Apply Feedback and Update Results job:

• Trains the model using the latest verified record categorizations.

• Applies the model to all records.

• Calculates record categorization confidences and their average.

📘

In order for the Apply Feedback and Update Results job to execute, the following conditions must be met:

• Must have one or more unified attributes specified as included in machine learning
• Must have a taxonomy associated with the project
• Cannot currently have a running job
• Unified dataset must be up to date

To update apply feedback and update categorization results:

1. Navigate to the Categorizations tab of a Categorization project.

2. Click Apply Feedback and update results.

Updating Categorization Results

📘

Update Results

The Update Categorizations job:

• Applies the model to all records.

• Calculates record categorization confidences and their average.

📘

The Update results job can only be run after at least one Apply feedback and update results job has been completed, or after a model has been imported for the project.

To update categorization results:

1. Navigate to the Categorizations tab of a Categorization project.
2. Click the arrow on the Apply feedback and update results button, and select Update results only.