- Getting started
- Balance
- Clusters
- Concept drift
- Coverage
- Datasets
- General fields (previously entities)
- Labels (predictions, confidence levels, hierarchy, etc.)
- Models
- Streams
- Model Rating
- Projects
- Precision
- Recall
- Reviewed and unreviewed messages
- Sources
- Taxonomies
- Training
- True and false positive and negative predictions
- Validation
- Messages
- Administration
- Manage sources and datasets
- Understanding the data structure and permissions
- Create a data source in the GUI
- Uploading a CSV file into a source
- Create a new dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amend a dataset's settings
- Delete messages via the UI
- Delete a dataset
- Delete a source
- Export a dataset
- Using Exchange Integrations
- Preparing data for .CSV upload
- Model training and maintenance
- Understanding labels, general fields and metadata
- Label hierarchy and best practice
- Defining your taxonomy objectives
- Analytics vs. automation use cases
- Turning your objectives into labels
- Building your taxonomy structure
- Taxonomy design best practice
- Importing your taxonomy
- Overview of the model training process
- Generative Annotation (NEW)
- Understanding the status of your dataset
- Model training and annotating best practice
- Training with label sentiment analysis enabled
- Train
- Introduction to Refine
- Precision and recall explained
- Precision and recall
- How does Validation work?
- Understanding and improving model performance
- Why might a label have low average precision?
- Training using Check label and Missed label
- Training using Teach label (Refine)
- Training using Search (Refine)
- Understanding and increasing coverage
- Improving Balance and using Rebalance
- When to stop training your model
- Using general fields
- Generative extraction
- Using analytics and monitoring
- Automations and Communications Mining
- Licensing information
- FAQs and more
Pruning and reorganising your taxonomy
User permissions required: 'View Sources' AND 'Review and annotate'.
To make any changes to labels (renaming, merging or deleting), you can access the label edit tool by clicking the cog icon that appears when you hover your mouse over the label name in Explore or Reports (as shown below).
Merging and deleting labels are actions that cannot be undone, so be careful when doing so. If you want to make considerable changes to your taxonomy but are concerned about the outcome, you can always fork the taxonomy first by creating a copy of the dataset and then you can revert back to the old version if you are unsatisfied with the changes.
Deleting a label
To delete a label – either because you created it by mistake or you no longer need it - you can do so by clicking the cog icon next to the label name.
- Click to the ‘Delete’ tab
- Then click ‘Delete label’
Merging a label
You may need to merge one label with another for a few different reasons. It might be that you’ve created two labels which are very similar and one label will suffice rather than two. It could also be that you’ve created very specific sub-labels and there are insufficient examples at that level of detail and you want to merge a label back up into its’ parent.
To merge one label into another, click the cog icon next to the name of the label that will be merged to bring up the label edit model (A).
- Click to the ‘Merge’ tab shown in (B)
- Select the other label that you want to merge the label into from the dropdown, or type it in
- Click ‘Merge label’
Renaming a label
Renaming a label is a simple (and reversible) process. This is why it’s ok not to worry what to call a label when first building your taxonomy. As long as you’re capturing the idea or concept with the label, you can change the name later.
To rename a label, click the cog icon next to the label name to bring up the label edit model (A):
- Click to the ‘Rename’ tab shown in (B).
- Type the new name for your label.
- Click ‘Rename label’.
Renaming a label is also the easiest way to move labels around and add layers of hierarchy to your taxonomy, like in this example. This label name change means that the ‘Room Temperature’ label will now be nested under the ‘Bedroom’ label. All ‘Room Temperature’ labels will now be considered a subset of ‘Bedroom’ by the model.