---
sourceDocument: Brazil Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences
Release :
- brazil
ft:locale :
- en-US
ft:publication_title :
- Brazil Enable AI
ft:clusterId :
- platai
bundleId :
- platai
workflow :
- Platform
---
# (Legacy) NLU vocabulary
# (Legacy) NLU vocabulary {#ariaid-title1}
Release version: Brazil
Updated September 10, 2026
 4 minutes to read
Summarize
 Summarized using AI
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.
## Summary of (Legacy) NLU vocabulary
The (Legacy) NLU vocabulary feature in ServiceNow helps your natural language understanding models recognize the diverse ways users express their requests.
By defining vocabulary items and vocabulary sources, you improve the system's ability to accurately predict user intents, increasing confidence and consistency in responses.
Show full answer Show less
## Key Features
* **Vocabulary Items:** These represent individual words, phrases, or patterns that map to synonyms used for intent prediction. They cover variations such as acronyms or industry-specific terms. Vocabulary items come in two types:
* **Regular:** Case-insensitive words or phrases, e.g., acronyms.
* **Pattern:** Regular expressions (regex) to capture specific formats such as capitalized terms, email addresses, or phone numbers, allowing precise intent prediction.
* **Vocabulary Sources:** These reference entire ServiceNow tables or static lists (e.g., conference rooms, catalog items). They allow you to represent sets of objects with a single synonym, simplifying utterance training and enabling reuse across multiple NLU models.
* **Intent Integration:** Vocabulary items replace their occurrences in utterances with synonyms, helping the model recognize different expressions of the same concept and improving prediction accuracy.
## Practical Applications
* Use vocabulary items to define acronyms or business-specific terms that users might say differently from their full names, raising the model's confidence in intent prediction.
* Use pattern vocabulary items with regex to distinguish terms that could be ambiguous otherwise, such as recognizing "Word" as a software product only when capitalized.
* Create vocabulary sources to reference dynamic or predefined lists of objects within your ServiceNow environment, enabling more scalable and maintainable intent training.
* Annotate specific words or phrases as entities in utterances to extract values for use in Virtual Agent conversations.
* Map multiple vocabulary items to a single synonym, but avoid mapping one vocabulary item to multiple synonyms to maintain clarity in intent recognition.
## Regex Usage Tips
Pattern vocabulary items support regex with default case sensitivity. To precisely match acronyms like "IT" without matching substrings (e.g., ITSM), use word boundary markers (e.g., \\bIT\\b). You can also enable or disable case sensitivity within your regex using syntax like (?i) and (?-i).
## Benefits for ServiceNow Customers
By leveraging legacy NLU vocabulary items and sources, you enable your conversational AI to better understand user language variations, improve intent prediction accuracy, and scale intent training efficiently with reusable vocabulary sources. This leads to more reliable Virtual Agent interactions and enhanced user satisfaction.
Use NLU vocabulary items to help the system recognize the various ways your users express their requests. Use vocabulary sources to help the system recognize objects in tables or lists, such as names of
conference rooms or catalog items.
## Vocabulary usage and context {#using-nlu-vocabulary__section_l2j_rdr_1nb}
Vocabulary helps your model with the various words and phrases that it may encounter from your users.
Since humans are not computers, they may come up with different ways to say the same thing. For example, if one user inputs an acronym rather than the full phrase, the system might be able to predict the correct intent by using
the context in the utterance. However, by defining the acronym with a vocabulary item, you raise the model's confidence level and capability to predict intents correctly.
Vocabulary items cover the varying words or phrases that might appear in utterances. The vocabulary items are mapped to the synonyms that you provide, for intent prediction. This helps the system recognize the various ways your
users express their requests, while at the same time ensuring the consistency, confidence, and accuracy of predictions.
## Vocabulary item types {#using-nlu-vocabulary__section_fjt_zbv_mlb}
NLU provides the following vocabulary types that you can use to create and configure a vocabulary item. {#using-nlu-vocabulary__table_k3t_dzw_h5b__entry__2}
| Type | Definition |
|-|-|
| Regular | A word or phrase that is not commonly known, such as a business or industry specific term or acronym. Regular vocabulary is case insensitive, so all case variations will be captured by the vocabulary you create. See [(Legacy) Create a regular vocabulary item](https://www.servicenow.com/docs/YlDWKgioyps5uB3wPgA~tw "Add a word or phrase that your users might use, and match that vocabulary item to a synonym. Your model uses the synonym during intent prediction."). |
| Pattern | A regular expression (regex) that can capture specific formats such as email addresses and phone numbers. See [(Legacy) Create a pattern vocabulary item](https://www.servicenow.com/docs/zUalhITWsODq7YNVIxuggw "Use regular expression (regex) encoding to establish a pattern format for vocabulary items such as email addresses, phone numbers, and record naming conventions. You can create your own patterns for the vocabulary data in your instance."). |
[ ]
{#using-nlu-vocabulary__table_k3t_dzw_h5b}
## Vocabulary sources {#using-nlu-vocabulary__section_jzy_zjp_knb}
You can also use vocabulary sources to cover various objects that your users might request. Vocabulary items and vocabulary sources differ in their usage:
* Use a vocabulary item for an individual word, phrase, or pattern that can easily be mapped to a single synonym for the model to use.
* Use a vocabulary source to reference a ServiceNow table or list so that the values can all be replaced by the single synonym you define. Vocabulary sources can be reused across all your NLU models.
{#using-nlu-vocabulary__ul_rs5_1vl_nrb}
Use vocabulary sources when your user utterances refer to objects in a set. The sources can be
referenced from a list of values from a ServiceNow table or a static list that you define, such as a list of catalog items or conference rooms. Once you create and save these sources, you can use the @ symbol to specify them in training
utterances. You can also use these sources as entity values.
For example, say you already have a list of all the conference rooms for your office. You can create a vocabulary source to reference that list rather than typing each conference room name into your intent's training
utterances.
To create vocabulary sources, refer to [(Legacy) Create a table vocabulary source](https://www.servicenow.com/docs/pmsuAfbCeRxiAg3ohaK3jQ "Use the values from a ServiceNow table as a vocabulary source. Your Natural Language Understanding (NLU) models use your provided synonym to interpret utterances that contain values from the chosen source fields of the table.")
and [(Legacy) Create a list vocabulary source](https://www.servicenow.com/docs/xi1VEi~VcSGxPaj2GYzr2w "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.").
## Vocabulary usage in relation to an intent {#using-nlu-vocabulary__section_gbf_vt1_bnb}
Here's an example of how an intent can interact with the vocabulary in its utterance examples.
Note:
In NLU vocabulary, the synonym replaces the vocabulary that appears in the utterance.
{#using-nlu-vocabulary__table_rn1_r4s_pwb__entry__2}
| Utterance | Issue and Solution |
|-|-|
| "I need to access sfcrm" | * Issue: the system doesn't recognize the acronym sfcrm, so can't accurately predict the intent. * Solution: Add sfcrm as a regular vocabulary item, and provide a synonym such as CRM software. {#using-nlu-vocabulary__ul_mfn_1ps_pwb} |
| "I need to install Word" | * Issue: The term word is very common and does not necessarily indicate a software product. The term install may provide helpful context, but the confidence score may be too low to predict the OrderSoftware intent. * Solution: Create a pattern vocabulary item with a regex for capitalized Word, so that the system can recognize it as a software product. This added constraint makes it more likely that the OrderSoftware intent will be predicted. Note: To extract the specific software name to use in a Virtual Agent conversation topic, annotate it as an entity in the utterance. {#using-nlu-vocabulary__ul_nms_kps_pwb} |
[Table 1. Intent: OrderSoftware]
{#using-nlu-vocabulary__table_rn1_r4s_pwb}
Use a single word or short phrase as a synonym for best results. You can map multiple vocabulary items to one synonym. Do not map one vocabulary item to multiple synonyms.
For more context and examples, see [(Legacy) Create an NLU intent](https://www.servicenow.com/docs/CWNGECudoLIy~TcfEQlskw "Create an intent for your Natural Language Understanding (NLU) model. Intents provide your model with a system action to perform when it receives user input.").
## A Regex example for a pattern vocabulary item {#using-nlu-vocabulary__section_aqg_ygv_mlb}
Let's say that you want to use a vocabulary item to identify the acronym IT, and map it to the synonym information technology.
Regular vocabulary items are case-insensitive by default. This means that a regular vocabulary item would match both the acronym IT and the common word it. So you decide to use a pattern vocabulary
item.
The regex pattern that you can use is \bIT\b. The \b is a word boundary marker. This ensures that the pattern would not match ITSM or JIT, for example. The
default case sensitivity of pattern vocabulary items means that \bIT\b would not match the common word it.
Regex details: You can turn off case sensitivity in a pattern by using (?i). You can end that mode by using a minus sign as in (?-i). For example,
(?i)te(?-i)st should match both test and TEst, but not teST or TEST.
For more information, see [(Legacy) Using regular expressions in entities](https://www.servicenow.com/docs/eRzfUbRkn_aTGLDVAuWR3w "Learn how to use regular expressions in your NLU entities to establish patterns that help the system locate, match, and manage text.").
**Related tasks**
* [(Legacy) Create an NLU intent](https://www.servicenow.com/docs/CWNGECudoLIy~TcfEQlskw "Create an intent for your Natural Language Understanding (NLU) model. Intents provide your model with a system action to perform when it receives user input.")