---
sourceDocument: Xanadu Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/xanadu/intelligent-experiences

 Release :

    - xanadu

ft:locale :

    - en-US

ft:publication_title :

    - Xanadu Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Create a list vocabulary source

# Create a list vocabulary source {#ariaid-title1}

* Release version: Xanadu
* 
* Updated January 10, 2025
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read

Create a list of words or phrases to act as a vocabulary source. The values in the
list source are replaced by the synonym if they are detected in a user
utterance.

## Before you begin

* Make sure that the NLU Workbench plugin, NLU Workbench - Core plugin, NLU Common Model plugin, and Predictive Intelligence plugin are all installed and activated on your instance.
* Role required: admin, nlu_admin, or nlu_editor
{#create-static-list-source__ul_shl_vvs_tgb}

## About this task

Creating a list vocabulary source enables your models to interpret all the alternate and actual values of the list if they appear in a user utterance. The model interprets those values as the synonym you provide when predicting an intent.  
Note:  
During intent prediction, the synonym you provide replaces the value. During entity prediction, the actual value is used as the entity if the actual value or one of the alternate values are detected in the utterance.

In this example procedure, you're creating a list vocabulary source for your
company's meeting rooms. You add the names of the rooms and alternatives your users
might call them. Once you create the list, you add it to an utterance in an intent
for the model. The model interprets the intent (for example, #BookMeetingRoom) and
uses the name the user entered as an entity (for example, Everest).

## Procedure

1. Navigate to AllNLU WorkbenchVocabulary Sources.
2. Click the My lists tab.
3. Click Create new list.  
4. In the Create a new list to refer to window, configure the fields.  
   {#create-static-list-source__table_g13_vfz_d5b__entry__2}

   | Field | Description |
   |-|-|
   | Handle | Name for the vocabulary source. Used to refer to in an utterance. |
   | Language | Language of the vocabulary source. Synonym must be in the same language. |
   | Synonym | Word or phrase the model uses during intent prediction. Choose a commonly-occurring word in the same language as your model. |
   | Enable Fuzzy Matching | Check this box if you want the items on the list to match when a user utterance has slight misspellings. |
   | Make case sensitive | Check this box to make the values in the list case sensitive. Utterances with wrong cases won't match. |
   [ ]

   {#create-static-list-source__table_g13_vfz_d5b}For this example, use the following configurations:
   * Handle: <kbd class="ph userinput">@meetingroom</kbd>
   * Language: <kbd class="ph userinput">English - en</kbd>
   * Synonym: <kbd class="ph userinput">meeting room</kbd>
   * Enable Fuzzy Matching: Select the box.
   * Make case sensitive: Leave the box clear.
   {#create-static-list-source__ul_ady_dyh_jsb}

5. Click Create.  
   Your list vocabulary source draft appears in the My lists section of the Vocabulary sources screen.
6. Click the name of the list vocabulary source.
7. Click Add list item.
8. Enter a value for the list and click the green check mark.  

   In this example, you enter <kbd class="ph userinput">Everest</kbd>.
9. Double-click the area under Alternate values to add alternatives separated by a comma.  
10. Train the model to make the list vocabulary source available.

## What to do next

Add the rest of the break room names and alternatives.

You must retrain the model after updating a list vocabulary source. For more
information, see [Train and try your NLU model](https://servicenow-prod.fluidtopics.net/4XbdTt0aQvTMtxtl8ueabA "Train and try your model iteratively so that its intents and entities are validated, compiled, and saved to your model.").

Then you can use the list vocabulary source when annotating a training utterance.
Use the @ symbol with the handle to refer to this vocabulary source.

*[\>]: and then