Azure AI Services CLU: Null Resolutions Block Returned for Quantity.Dimension Entity

Mark 30 Reputation points
2025-08-17T20:09:28.7766667+00:00

Azure AI Services CLU (conversational language understanding) returns a null Resolutions block in results for the built-in Quantity.Dimension entity. This was working normally as of a week or two ago. Other built-in entities return the Resolutions block as expected. So far, it's just the Dimension entity that seems to be affected.

You can see the behavior directly in Azure AI Language Studio / Testing Deployments and examining the Result JSON. I've had the same model deployed and working properly for 9 months prior to this.

I tried training the same model again and deployed it as a new version to a Test endpoint with the same results.

I haven't seen the issue raised anywhere else yet.

Region: North Europe

Below is a sample Result output illustrating the issue with the Quantity.Dimension built-in entity. See 'category': 'dimension' below...

{
  "query": "show me the first 10 items within 20 km of gromo, italy last year\n\n\n",
  "prediction": {
    "topIntent": "Scrapbook.Find",
    "projectKind": "Conversation",
    "intents": [
      {
        "category": "Scrapbook.Find",
        "confidenceScore": 1
      },
      {
        "category": "Scrapbook.ShowAssets",
        "confidenceScore": 1.9243291e-9
      },
      {
        "category": "Scrapbook.Where",
        "confidenceScore": 1.2294839e-10
      },
      {
        "category": "Scrapbook.Reset",
        "confidenceScore": 8.733761e-11
      },
      {
        "category": "Scrapbook.Count",
        "confidenceScore": 8.1913414e-11
      },
      {
        "category": "Scrapbook.Welcome",
        "confidenceScore": 7.377301e-11
      },
      {
        "category": "Scrapbook.Navigate",
        "confidenceScore": 4.3238208e-11
      },
      {
        "category": "Scrapbook.DrillDown",
        "confidenceScore": 4.2078348e-11
      },
      {
        "category": "Scrapbook.Collection",
        "confidenceScore": 1.2524555e-11
      },
      {
        "category": "Scrapbook.Category",
        "confidenceScore": 4.101284e-12
      },
      {
        "category": "Scrapbook.Related",
        "confidenceScore": 3.3869298e-12
      },
      {
        "category": "None",
        "confidenceScore": 2.362469e-12
      },
      {
        "category": "Scrapbook.SelectItem",
        "confidenceScore": 1.6680388e-12
      },
      {
        "category": "Scrapbook.ShowDetails",
        "confidenceScore": 1.1624435e-12
      },
      {
        "category": "Scrapbook.Help",
        "confidenceScore": 6.251971e-13
      },
      {
        "category": "Scrapbook.Debug",
        "confidenceScore": 2.110486e-13
      },
      {
        "category": "Scrapbook.Goodbye",
        "confidenceScore": 1.6217763e-13
      }
    ],
    "entities": [
      {
        "category": "ordinal",
        "text": "first",
        "offset": 12,
        "length": 5,
        "confidenceScore": 1,
        "resolutions": [
          {
            "resolutionKind": "OrdinalResolution",
            "offset": "1",
            "relativeTo": "Start",
            "value": "1"
          }
        ],
        "extraInformation": [
          {
            "extraInformationKind": "EntitySubtype",
            "value": "quantity.ordinal",
            "tags": [
              {
                "name": "Ordinal",
                "confidenceScore": 0.6
              },
              {
                "name": "Numeric",
                "confidenceScore": 0.6
              }
            ]
          }
        ]
      },
      {
        "category": "l.param",
        "text": "first",
        "offset": 12,
        "length": 5,
        "confidenceScore": 1,
        "extraInformation": [
          {
            "extraInformationKind": "ListKey",
            "key": "earliest"
          }
        ]
      },
      {
        "category": "number",
        "text": "10",
        "offset": 18,
        "length": 2,
        "confidenceScore": 1,
        "resolutions": [
          {
            "resolutionKind": "NumberResolution",
            "numberKind": "Integer",
            "value": 10
          }
        ],
        "extraInformation": [
          {
            "extraInformationKind": "EntitySubtype",
            "value": "quantity.number",
            "tags": [
              {
                "name": "Number",
                "confidenceScore": 0.8
              },
              {
                "name": "Quantity",
                "confidenceScore": 0.8
              },
              {
                "name": "Numeric",
                "confidenceScore": 0.8
              }
            ]
          }
        ]
      },
      {
        "category": "l.category",
        "text": "items",
        "offset": 21,
        "length": 5,
        "confidenceScore": 1,
        "extraInformation": [
          {
            "extraInformationKind": "ListKey",
            "key": "any"
          }
        ]
      },
      {
        "category": "l.near",
        "text": "within",
        "offset": 27,
        "length": 6,
        "confidenceScore": 1,
        "extraInformation": [
          {
            "extraInformationKind": "ListKey",
            "key": "nearby"
          }
        ]
      },
      {
        "category": "number",
        "text": "20",
        "offset": 34,
        "length": 2,
        "confidenceScore": 1,
        "resolutions": [
          {
            "resolutionKind": "NumberResolution",
            "numberKind": "Integer",
            "value": 20
          }
        ],
        "extraInformation": [
          {
            "extraInformationKind": "EntitySubtype",
            "value": "quantity.number",
            "tags": [
              {
                "name": "Number",
                "confidenceScore": 0.8
              },
              {
                "name": "Quantity",
                "confidenceScore": 0.8
              },
              {
                "name": "Numeric",
                "confidenceScore": 0.8
              }
            ]
          }
        ]
      },
      {
        "category": "dimension",
        "text": "20 km",
        "offset": 34,
        "length": 5,
        "confidenceScore": 1
      },
      {
        "category": "geoLocation",
        "text": "gromo, italy",
        "offset": 43,
        "length": 12,
        "confidenceScore": 1,
        "extraInformation": [
          {
            "extraInformationKind": "EntitySubtype",
            "value": "geography.location",
            "tags": [
              {
                "name": "City",
                "confidenceScore": 1
              },
              {
                "name": "GPE",
                "confidenceScore": 1
              },
              {
                "name": "Location",
                "confidenceScore": 1
              }
            ]
          },
          {
            "extraInformationKind": "EntitySubtype",
            "value": "geography.location",
            "tags": [
              {
                "name": "CountryRegion",
                "confidenceScore": 0.99
              },
              {
                "name": "GPE",
                "confidenceScore": 0.99
              },
              {
                "name": "Location",
                "confidenceScore": 0.99
              }
            ]
          }
        ]
      },
      {
        "category": "dateTime",
        "text": "last year",
        "offset": 56,
        "length": 9,
        "confidenceScore": 1,
        "resolutions": [
          {
            "resolutionKind": "TemporalSpanResolution",
            "timex": "2024",
            "begin": "2024-01-01",
            "end": "2025-01-01"
          }
        ],
        "extraInformation": [
          {
            "extraInformationKind": "EntitySubtype",
            "value": "datetime.daterange",
            "tags": [
              {
                "name": "DateRange",
                "confidenceScore": 0.8
              },
              {
                "name": "DateTime",
                "confidenceScore": 0.8
              }
            ]
          }
        ]
      }
    ]
  }
}


Azure AI Language
Azure AI Language
An Azure service that provides natural language capabilities including sentiment analysis, entity extraction, and automated question answering.
{count} votes

Answer accepted by question author
  1. Manas Mohanty 13,340 Reputation points Moderator
    2025-09-29T01:37:17.3766667+00:00

    Hi Mark

    Sorry for long delay in fix from product group.

    Product group has confirmed on 25th Sep 2025 that they have created a fix which is pending deployment next week.

    Thank you for providing the inputs and giving the product team needed time to roll back the changes.

    1 person found this answer helpful.

1 additional answer

Sort by: Most helpful
  1. Sina Salam 26,661 Reputation points Volunteer Moderator
    2025-09-28T19:05:17.5433333+00:00

    Hello Mark,

    Welcome to the Microsoft Q&A and thank you for posting your questions here.

    This issue is getting too long, and my advice for you to resolve are the followings:

    1. Since the resolutions block is deprecated in newer CLU API versions (e.g., 2023-04-15-preview), you should now rely on the extraInformation field for structured data like units and values. This metadata replaces the old resolution format and is accessible via the CLU response JSON. Entity Resolutions → Metadata for more details.
    2. To handle missing resolution blocks for Quantity.Dimension, use a Regex component to match patterns like \d+\s?(km|m|mi|ft) or a List component to define expected units. These components allow manual extraction of values when built-in entities fail. CLU Entity Components
    3. Create a custom entity using a learned component trained on examples such as "20 km" or "5 meters". This approach enables the model to extract and normalize values even when built-in entities regress or behave inconsistently. CLU Configuration Guide
    4. Ensure you're using a supported API version like 2022-10-01-preview or later, as older versions may not support metadata or updated entity behavior. Always verify the modelVersion and api-version in your request headers. API Versioning for CLU
    5. Utilize the Azure.AI.Language.Conversations SDK to inspect raw CLU responses and debug missing fields. This helps validate whether metadata is present and how entities are parsed.
    6. Raise support ticket by yourself via your Azure Portal or use https://learn.microsoft.com/en-us/azure/azure-portal/supportability/priority-community-support (PCS).

    I hope this is helpful! Do not hesitate to let me know if you have any other questions or clarifications.


    Please don't forget to close up the thread here by upvoting and accept it as an answer if it is helpful.

    0 comments No comments

Your answer

Answers can be marked as 'Accepted' by the question author and 'Recommended' by moderators, which helps users know the answer solved the author's problem.