Correcting existing entities

Since Pega Email Bot does not automatically know how to respond, to ensure that the system detects the right entities in emails, correct the wrongly detected entities in the training data. When the email bot learns to detect the correct topics, entities, and language in emails, the artificial intelligence algorithms provide better responses to users. For example, you can correct an entity for the car make so that the system uses this information as a property in a business case that is related to a car insurance quote. For more information, see Setting up entity property mapping.
Before you begin: Enable the recording of training data. For more information, see Enabling the training data recording for an email bot.
  1. In the header of Dev Studio, click the name of the application, and then click Channels and interfaces.
  2. In the Current channel interfaces section, click the icon that represents your existing Email channel.
  3. On the Email channel configuration page, click the Training data tab.
  4. Optional: If you configure multiple languages for the email bot, to filter data records by a language, in the Language list, select a language.
    For example: To display data records only detected in the Spanish language, select Spanish.
  5. In the list of training records, select a data record.
    Result: The Review training data pane displays the detected entities and the NLP analysis section displays the entity types for the training data record.
  6. In the Review training data section, in the data record content, highlight and right-click the text for an existing entity, and then click the name of another entity.
    For example: To make sure the car make in the text maps to the CarMake entity, highlight and right-click Ford, and then click #CarMake.
  7. Optional: To use this training record to improve the artificial intelligence algorithm of your email bot, in the Review training data section, click Mark reviewed.
    Create at least 15 records in the training sample so that the system learns how to detect the right information in emails.
  8. Optional: To correct entities in additional training records, repeat steps 4 through 7.
    You can also manually create a sample training data record in the email bot. For more information, see Creating training data manually for an email bot.
  9. Click Save.
What to do next: Teach the email bot the reviewed and corrected training records by rebuilding the text analytics model. For more information, see Applying changes to a text analytics model for an email bot.