communications-mining
latest
false
Communications Mining User Guide
Last updated Sep 4, 2024

Importing your taxonomy

You can upload your taxonomy of labels to the Communications Mining platform from a spreadsheet. Uploading your taxonomy from a spreadsheet automatically imports all the labels without having to manually add them during model training.

To import your taxonomy from a spreadsheet, follow these steps:

  1. Select Settings on the navigation bar, then Taxonomy and Labels and extraction fields.
  2. Select the drop-down arrow next to the New label button.
  3. Select Import from spreadsheet from the drop-down list.
  4. Copy-paste your labels (Parent label > Child label format) and their descriptions (if available) from your spreadsheet.
  5. Select Import.




Note: It is highly recommended to add label descriptions to your labels to ensure annotating consistency. Adding label descriptions is particularly helpful if you have several people training the model.

To import your taxonomy from another dataset, follow these steps:

  1. Select the drop-down arrow next to the New label button.
  2. Select Import from dataset from the drop-down list.
  3. Select a dataset name from the drop-down list.
  4. Select Import.
Note: This copies labels and descriptions only from an existing dataset. To copy an entire dataset, including annotations and sources, select Duplicate from the dataset options in the Datasets page.


Manually imported or created labels in the taxonomy view

Adding pre-trained labels

You can also add pre-trained labels in this step. Pre-trained labels such as OOO, Thank-you, Urgent, Chaser, etc.) are generic concepts that have been pre-trained on a large pool of data.



  • Adding pre-trained labels

Was this page helpful?

Get The Help You Need
Learning RPA - Automation Courses
UiPath Community Forum
Uipath Logo White
Trust and Security
© 2005-2024 UiPath. All rights reserved.