NLU Service updates

  • Release version: Zurich
  • Updated July 31, 2025
  • 2 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 NLU Service updates

    The NLU (Natural Language Understanding) Service in ServiceNow enables your instance to interpret and process natural language input, whether spoken or written. It powers the training and prediction of user intents and entities within your NLU models, which is crucial for building intelligent Virtual Agent conversations and other automated language-driven workflows.

    Show full answer Show less

    This service is updated independently from your instance upgrades, with bi-monthly minor improvements and major updates aligned with major ServiceNow releases (e.g., Rome, San Diego, Tokyo). Updates are applied automatically without requiring action from you, ensuring you always use the latest enhancements when retraining your NLU models.

    Key Features and Enhancements

    • Dialog Acts in Virtual Agent (May 2023): Introduced dialog acts such as affirm, negate, and modify to support more natural mid-conversation interactions in English, enabled by default for new VA topics.
    • Language Model Improvements: Migrated all languages to new language models, increasing average intent prediction quality by 10% across languages (May 2023). Upgraded Nordic language models (Danish, Swedish, Finnish, Norwegian) with a 17% quality boost since Tokyo release (January 2023).
    • Irrelevance Detection: Enabled customers to manage and edit irrelevant utterances to fine-tune model irrelevance filtering (May 2023).
    • Model Configuration Flexibility: Removed the requirement for NLU models to have multiple intents, simplifying end-to-end topic testing in Virtual Agent (May 2023).
    • Intent/Entity Detection Enhancements: Improved processing of common words in vocabulary sources and enhanced system entity (NER) detection efficiency and latency (March 2023).
    • New System Entities and Language Support: Added a DATE-TIME system entity for English (January 2023). Expanded vocabulary and entity support to Dutch, Italian, Portuguese, and Brazilian Portuguese languages.
    • Handling of Punctuation and Special Characters: Enhanced entity recognition accuracy by better managing punctuation and special characters in vocabulary sources (January 2023).
    • Feedback Integration: Incorporated administrator feedback on intent predictions from the NLU Workbench to improve training data quality for Virtual Agent (January 2023).

    What This Means for You

    • Your NLU models benefit from ongoing improvements in accuracy, efficiency, and language support without manual intervention.
    • New capabilities like dialog acts enable more fluid and natural Virtual Agent conversations, improving user experience.
    • Greater flexibility in model design and enhanced irrelevance management empowers you to maintain and optimize your NLU models more effectively.
    • Staying current with the latest NLU Service versions ensures compatibility and access to the newest features and quality improvements.

    Refer to this documentation so you are up to date with changes to the NLU Service.

    Service update summary

    The NLU Service helps the system to understand natural language and drive intelligent actions. This service trains and predicts intents and entities for a given user utterance in your NLU model so it can understand human-expressed natural language, whether spoken or written. The source of this documentation is KB0953693.

    This service is updated independently of your instance upgrade, and without any action required by you. These updates are done on a bi-monthly basis (once every two months) to improve the quality of NLU model training and predictions. Major updates are aligned with family releases such as Rome, San Diego, Tokyo, etc. Minor updates are automatically updated so you are using the latest version when you retrain an NLU model. While most of these updates don't impact your existing use of NLU, there may be some changes you need to be aware of.

    May 2023 NLU Service update

    • Introduced dialog acts to enable natural mid-conversation in Virtual Agent (VA) and improve conversation fluidity. Affirm, negate, and modify dialog acts are supported in English and enabled by default for all new VA topics.
    • Migrated all languages to use new language models, boosting average intent prediction quality by 10% across all languages.
    • Enabled customers to manage and edit irrelevant utterances for their models to improve irrelevance detection.
    • Removed the requirement for a model to have 2 or more intents in the model, making it easier for end-to-end topic testing in VA.

    March 2023 NLU Service update

    • Improved intent/entity detection through better handling of common words in vocabulary sources.
    • Improved latency and memory utilization for system entity (NER) detection.
    • Updated version support so that customers will need to use newer versions of the NLU Service and cannot point to n-2 releases older than their current glide version.

    January 2023 NLU Service update

    • Created the new DATE-TIME system entity (English only) for use in Virtual Agent.
    • Added vocabulary source and entity support (simple, mapped, and open ended) for the Dutch and Italian languages, and system entity support for Portuguese and Brazilian Portuguese.
    • Upgraded the ServiceNow Language Model for the Danish, Swedish, Finnish, and Norwegian languages, improving their average prediction quality by 17% from Tokyo.
    • Improved the handling of punctuation in entities and special characters in vocabulary sources.
    • Incorporated feedback provided on intent predictions by admin users in the NLU Workbench to improve model training data for Virtual Agent.