Natural Language Understanding release notes

ServiceNow® Natural Language Understanding is a new platform capability in the New York release.

Natural Language Understanding (NLU) provides an NLU model builder and an NLU inference service that you can use to enable the system to learn and respond to human-expressed intent. By entering natural language examples into the system, you help it understand word meanings and contexts so it can infer user or system actions.

Natural Language Understanding features

NLU model builder: Use the NLU model builder to create morphological representations of language. These models enable you to identify intents (what you want to do or what you want your application to handle) and entities (the context or details for an action) expressed in natural language. Any ServiceNow application can invoke an NLU model to get an inference of intents and entities in a given utterance. For a description of this tool and how you can use it, see Natural Language Understanding.
Create an NLU model: Create an NLU model that the system uses to recognize and process user utterances, intentions (intents), and objects of, or contexts for, an action (entities). Train the model dataset iteratively using utterance examples so that the system predicts the optimal intent output for a new utterance.
Create an NLU intent: Create one or more intents for your NLU model based on utterance examples of what a user might say related to the intent.
Create a simple entity: Create one or more simple entities from words in your utterance examples. An entity is an object of, or context for, an action.
Annotating entities: When you create an NLU entity, you can annotate it with synonyms and other definitions. Learn the details required for you to annotate list and pattern entities properly.
Using regular expressions in entities: Learn how to use regular expressions in your NLU entities to create patterns that help the system match, locate, and manage certain text.
Train and test your NLU model: Train and test your model iteratively so that its intents and entities are validated and compiled, and your model is assigned a version number.
Publish your NLU model: Publish your model so that its most recent version is active.

Activation information

Activate the NLU model builder: Activate two natural language understanding (NLU) plugins and the Predictive Intelligence plugin so that Natural Language Understanding is active in your instance.

Browser requirements

For optimal performance on the Now Platform, use the NLU model builder in the latest release of Chrome, Safari, Firefox, and Edge. NLU model builder isn't supported in Internet Explorer.

Accessibility information

All NLU screens are WCAG-A and WCAG-AA compliant, with keyboard and screen reader support. Accessibility details for NLU utterances and entity annotations include the following.

You can tab to an utterance and use Arrow keys to move across words in the utterance. Pressing the Space or Enter key on a word opens the picker.
Search is in focus by default.
For Simple Entities on an utterance, the Down arrow selects the first item in the left panel of the picker.
For the first listed entity in the picker, the Right arrow selects the first item in the next panel to the right.
The Up/Down arrow takes you to the previous or next item, respectively.
Pressing the Space or Enter key selects that item and moves the focus to the first item in the next panel to the right.
Pressing Shift + Tab on the search field returns focus to the selected word and extends the selection range with the Shift + arrow keys.

Localization information

Natural Language Understanding is only available in the English language.

Contents