Microsoft

Language Understanding (LUIS)

Welcome to the LUIS API Forum

(Language Understanding Intelligent Service)

Categories

Documentation – Any ideas or suggestions for the API Reference or Documentation.

Language Support – Submit a request to have a particular language supported.

luis.ai WebApp – Ideas and suggestions for luis.ai and functionality used through the WebApp.

Programmatic API – Any ideas or feedback pertaining to features or enhancements to LUIS programmatic API.

Samples & SDK Request – Let us know if you would like to see a tutorial/sample or a SDK provided.


                               Attention!





We have moved our Customer Feedback & Ideas for Azure Cognitive Services portal to the Azure Feedback Forum.





Please go to the link below to access our new Feedback and Ideas Page.



  • Hot ideas
  • Top ideas
  • New ideas
  • My feedback
  1. Utterance Limit Reported When I have 0 Utterances in my Application

    BadArgument: The number of examples per application version cannot exceed the limit 15000. This is what I get when I try to add new utterances (examples) to an intent. The version of the app I am using has 0 utterances currently. I have repeatedly added and deleted intents, utterances and entities programmatically in the past, but I don't think that utterances I have deleted should count. Shouldn't I be allowed to add new utterances?

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  3 comments  ·  Utterances  ·  Flag idea as inappropriate…  ·  Admin →
  2. Batch Test Results - Overall doesn't total correctly

    I have 61 intents in a dataset in the batch test results. When I push run, in the right scroll panel with all of the intents (and entities listed) I see at the top "overview (44/61 utterances passed)" However if I view each intent individually, I see just 1 FP and 1 FN across all the intents. Therefore, the total should be much higher than 44, perhaps 59 I would have think about the exact total. This should be fixed or at least clarified to the user doing the testing how the 44 was arrived at since it seems to…

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  luis.ai WebApp  ·  Flag idea as inappropriate…  ·  Admin →
  3. Show which utterances were ignored due to missing intents

    "Note: 1 utterance(s) were ignored due to missing intents." I cannot find which intent Luis thinks is missing. It would save so much time if I could quickly display it. It could be something as simple as a stray type which takes forever to find.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  luis.ai WebApp  ·  Flag idea as inappropriate…  ·  Admin →
  4. Speech on LUIS Dashboard

    I have subscribed to speech services and can integrate speech utterance results into a call to a LUIS app to predict the instance. My question is can I test speech with my LUIS app from the Dashboard? DialogFlow provides this capability and it would very useful here too.

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  luis.ai WebApp  ·  Flag idea as inappropriate…  ·  Admin →
  5. Github integration for revisions

    GitHub integration for both experimentation and security.


    1. Commit. We would like to take snapshots of our Luis apps and easily commit those changes into GitHub. Ideally this would be a simple matter of "export" followed by a "commit + push" and then all the necessary files associated with the app would be exported.


    2. Restore. We could also easily restore snapshots (of course). If there is a work around, would love to hear about it.


    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Programmatic API  ·  Flag idea as inappropriate…  ·  Admin →
  6. include SmallTalk Intent in Pre-Built

    I would like to suggest LUIS should include the Pre-Built Intent for SmallTalk.

    6 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Intents  ·  Flag idea as inappropriate…  ·  Admin →
  7. Provide Shareable Authoring Keys

    We deploy LUIS as part of a CI/CD pipeline for our application. Currently, this requires manually storing a developer's authoring key in our devops service, and using that key to create and manage our production LUIS apps.

    This is bad for two reasons:


    1. The developer whose key is used has the ability to modify or delete our production LUIS apps, bypassing our change control system.

    2. If this developer leaves, we'll need to use the authoring key of somebody else on the team, which will require creating new apps and potentially disrupting our service.

    It would be great if we got…

    4 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Programmatic API  ·  Flag idea as inappropriate…  ·  Admin →
  8. Possibility to customize output structure

    In the output folder of the LUIS.ai docker container, the structure is "/output/luisai/dockercontainerid/app_id.csv

    The problem is, that when i stop/start the docker container, the docker container id changes, and therefore the csv output files are now in another output subfolder. Is there a possibilty to skip the folder with the docker container id?

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  luis.ai WebApp  ·  Flag idea as inappropriate…  ·  Admin →
  9. Speech: support of custom speech models from CRIS

    As some of our vocabulary is really domain-oriented, it would be interesting to be able to point to a Custom Speech endpoint instead of generic speech endpoint in an "all-in-one" transaction (from speech to intent recognition)

    4 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Programmatic API  ·  Flag idea as inappropriate…  ·  Admin →
  10. Improve brackets in patterns

    A pattern such as sho[w] should match both "sho" and "show". Below are some examples of the current behavior. There are many more use cases in German and other languages. This feature would simplify and shorten pattern creation significantly.

    Pattern: [show][sho] me the cash
    Match: sho me the cash
    Match: show me the cash

    Pattern: sho[w] me the money
    Match: sho me the money
    No match: show me the money
    Match: sho w me the money

    7 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Patterns  ·  Flag idea as inappropriate…  ·  Admin →
    Under Review  ·  Luke Bayler responded

    Hello,

    Our pattern engine currently doesn’t support this because anything in between spaces is considered as a token. We can look into adding this.

    In the meantime, you can do this with pipes (“|”). For example, (show | sho) me the money.

    Thanks,
    Luke

  11. Ability to review the untrained changes before hit the train button

    Once new utterances has entered or deleted or other changes the Train button shows the App has untrained changes. Before hit the train button , it will be a good idea to review what changes we made. This is ideal for multi user environment.

    21 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  luis.ai WebApp  ·  Flag idea as inappropriate…  ·  Admin →
  12. More than 10 batch tests

    Currently batch testing panel is limited to 10 batches. I prefer to have 1 batch for each intent as we have hundreds of tests for each intent. We currently have 12 intents and are still growing.

    Not sure why the batch testing panel is capped at 10, should allow any # of batches.

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Service Limits  ·  Flag idea as inappropriate…  ·  Admin →
  13. Gherkin language processing for BDD automated testing

    Really random idea. Could LUIS process natural language to automate tests?

    Given the account balance is $100
    And the card is valid
    And the machine contains enough money

    When the Account Holder requests $20
    Then the ATM should dispense $20
    And the account balance should be $80
    And the card should be returned

    These lines and similarly phrased lines, could be deconstructed into tokens that match setting tests up and checking results. Right?

    So we could speak out a test suite.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Programmatic API  ·  Flag idea as inappropriate…  ·  Admin →
  14. Allow placeholders in utterances

    Allow placeholders in utterances to facilitate a persons name (as with creating Patterns)

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Utterances  ·  Flag idea as inappropriate…  ·  Admin →
  15. Luis can not recognition my entity defined in chinese

    I create entity in Chinese,include entity‘s name and items .
    And my situation is Luis can not recognition my entity by the function named TryFindEntity().
    Is Luis don't support Chinese now?

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Language Support  ·  Flag idea as inappropriate…  ·  Admin →
  16. Specify cardinality of entities within a composite entity

    It would be useful to have the ability to specify if we expect sub-entities to appear once or multiple times in composite entities. In some cases, utterances may contain multiple instances of the same composite entity, each with only one instance of the sub-entities. Right now, since there is no way to provide this information, they get aggregated in the same composite entity.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Entities  ·  Flag idea as inappropriate…  ·  Admin →
  17. Wrong flow in website

    Hi, this is the offending page URL: https://azure.microsoft.com/en-us/services/cognitive-services/language-understanding-intelligent-service/
    There are a number of scenarios, like Information Chatbot, etc. At least in the first two scenarios, flow steps and numbers on the diagram do not seem to match. I happen to notice that first because I read the same scenarios in another page: https://dev.botframework.com/
    On that page the diagrams are slightly different, but the flow is the same and the numbers on diagram are consistent.
    As an example of wrong numbering on LUIS home page, compare its Information Chatbot diagram with the one from Bot Framework page:
    number 7 should be…

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  18. Bug: Increasing the length of utterance with garbage value increases the score

    Adding any special character to the trailing, leading or in between words or junk or irrelevant text leads to very high score intent. It seems the length of the sentence is directly proportional to the score , can you please explain?

    0 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Utterances  ·  Flag idea as inappropriate…  ·  Admin →
  19. Callback or long poll support for app training

    Create a mechanism to be notified when an app has completed training.

    Currently we need to poll the train endpoint to monitor the status. I would find it less expensive and error prone to have an option to long poll; leave the connection open for a period of time.

    Or if we could register a callback endpoint, that would work as well.

    Thanks!

    4 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Programmatic API  ·  Flag idea as inappropriate…  ·  Admin →
  20. Luis Error Fuzzy search switched off as default. So no help here ??

    Hi there, I have issues with Luis. It does not allow someone to use fuzzy search as default. If I enable it, it goes off after opening the intents again..

    What's the problem. Usually what I know fuzzy search should enable it self by default but now now or you can't apply it anymore ??

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  luis.ai WebApp  ·  Flag idea as inappropriate…  ·  Admin →
← Previous 1 3
  • Don't see your idea?

Feedback and Knowledge Base