Training
Identify and quickly train unrecognized user inputs in your NLX workspace
Last updated
Identify and quickly train unrecognized user inputs in your NLX workspace
Last updated
Training lists all user utterances that triggered an application's because intent could not be identified. Training allows you to add unknown user messages to existing training data, refine existing training data to better adapt to user language, or to identify possible actions or intent flows your users require.
To manage training your NLP models, click Training in your workspace menu:
The Unknown tab lists all utterances or inputs from users that were unrecognized and were unable to match to an intent with confidence.
Unknown messages are organized by the following:
Text: The user input or utterance
Sent: Date the input or utterance was made
Confidence score: The confidence level of the NLP in matching the user's utterance
Intent: The intent (flow) that the NLP routed the user to
Trained intent: If trained, displays the intent (flow) the user input was added to
Clusters group user utterances semantically, providing you with a visual presentation of key topics commonly queried by your users. They can provide insight into the needs of users as well as opportunities for automation:
Please contact your customer success representative to enable this feature in your workspace, if currently unavailable.
Toggle between Table or Map view to change the visual presentation of captured clusters. Clusters provide the following information:
Label: The semantic description provided to the cluster group (can be renamed by typing in the Label field in Table view)
Phrases: The number of user inputs (with total percentage) that comprise the cluster
Intents: The number of intents where user inputs matching the semantic cluster appeared
Subclusters (only visible in Table view): The number of individual sub groups that comprise the cluster. Expand each cluster row to view
Hover over a row and select the Expand icon (in Table view) or select the card (in Map view) to view advanced details, including all intents and timestamp of phrases.
You may use any filter to narrow the results by Application, Intent, Region, Language, Start & End times, Channel, exact text (Search), and/or Confidence score. Results automatically update as filters are applied.
You may easily add an unknown user utterance as a training phrase to better train your application's AI model(s) when identifying customer intent and matching to the correct flow.
Select Training from workspace menu > Click the checkbox to the right of the message you wish to train
Choose Train intent link. You can select as many items as you'd like, but they will all be added to the same intent flow's training data
Select an intent from the dropdown
Select/deselect language(s) associated with the chosen intent
Enter any phrase adjustments to alter the inputs (messages will otherwise be added to an intent's list of Training phrase as they appear)
Click Confirm
Unknown messages remain in the list, even if training has occurred. appear with information under the Trained intent column.
Unknowns: The number of times the user input triggered the application's
Trained messages remain with information under the Trained intent column and as part of an intent flow's .
Be sure to create a your application to experience any changes.
