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.
-
Delete Utterances on the 'Review Endpoint Utterances' page not working
The new interface for 'Review Endpoint Utterances' doesn't delete utterances when the delete button is clicked.
1 vote -
"Batch add labels" already in progress returns error code 400 instead of 409
It is very difficult to isolate "Batch add labels already in progress" errors, because contrary to what is stated in the docs, API returns error code 400 instead of 409.
1 vote -
Should not modify the design often
We often encounter the phenomenon that the sentence we can parse does not work because of the change of LUIS. As a user, we hope that LUIS will consider the impact on the user when changing the design.
1 vote -
1.0.2 tokenizer for dutch
Because a lot of words used in utterances and entities are split in German, a new tokenizer is available for this language. In Dutch the problem is exactly the same. It would be really helpful if the other tokenizer was also available in Dutch.
8 votes -
Places.Destination / GeographV2 Builtin
Why did Places.Destination get deprecated? That worked great for mapping a variety of locations to an entity. The GeographyV2 entity only recognized well known places. You cannot map a small city like west chester PA to a geography entity. So you are forced to make a simple entity that will work for all location formats (New York City / Albany NY / 19431 / Missouri / Philadelphia Pennsylvania etc.). Now it says that GeographyV2 is also getting deprecated and it won't even break the entity into .city, .state, .region. What a drag. Any suggestions?
1 vote -
Can't use azure endpoint key in a lot of LUIS apps
I have several LUIS apps, 6 normal and 5 dispatch. I assign the same endpoint key from a cognitive service en Azure to all of them. But it seems that there are always two that end up losing the resource somehow. Couldn't find any documentation about a limit on how many LUIS apps can use the same endpoint at the same time.
2 votes -
App Endpoint Setting doesn't display accurate data
When looking at the App Endpoint Settings of different apps, I have to press F5 to see the actual resources assigned to that app, if not it displays a mix of different resources of previously visited apps
1 vote -
Paragraph comprehension Bot
Is there a way in Bot Framework to enter a paragraph as an uterrance and user asks questions from that paragraph and LUIS answers those question? If not then please introduce this feature
2 votes -
Unstructured errors are not proper JSON as reported in the Content-Type header
API responses that are unstructured report via the Content-Type header that they are of type "application/json" but are not valid JSON. Here's an example response:
HTTP/1.1 410 Gone
Content-Length: 87
Apim-Request-Id: 7da07e7b-bc03-480e-bce0-9308a82ee3c8
Cache-Control: no-store, proxy-revalidate, no-cache, max-age=0, private
Content-Type: application/json; charset=utf-8
Date: Tue, 14 May 2019 19:54:46 GMT
Pragma: no-cache
Request-Context: appId=cid-v1:26a3540d-a02a-4998-a060-715488fd769b
Request-Id: 7da07e7b-bc03-480e-bce0-9308a82ee3c8
Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
X-Content-Type-Options: nosniff
X-Frame-Options: SAMEORIGINThe application d41caa76-af3c-4091-8ee6-0113f22176fe is not published or doesn't exist.
1 vote -
Luis.LuisRecognizer.RecognizeAsync input string was not in a correct format
When sending from Bot to LUIS sentence containing "087654308754433656786" I am getting Exception:
"input string was not in a correct format"
at System.Number.ParseDouble(ReadOnlySpan1 value, NumberStyles options, NumberFormatInfo numfmt)1 entities, IList`1 compositeEntities, Boolean verbose) in D:\a\1\s\libraries\Microsoft.Bot.Builder.AI.LUIS\LuisRecognizer.cs:line 182
at Microsoft.Bot.Builder.AI.Luis.LuisRecognizer.Number(Object value) in D:\a\1\s\libraries\Microsoft.Bot.Builder.AI.LUIS\LuisRecognizer.cs:line 200
at Microsoft.Bot.Builder.AI.Luis.LuisRecognizer.ExtractEntityValue(EntityModel entity) in D:\a\1\s\libraries\Microsoft.Bot.Builder.AI.LUIS\LuisRecognizer.cs:line 236
at Microsoft.Bot.Builder.AI.Luis.LuisRecognizer.ExtractEntitiesAndMetadata(IList
at Microsoft.Bot.Builder.AI.Luis.LuisRecognizer.RecognizeInternalAsync(ITurnContext turnContext, CancellationToken cancellationToken) in D:\a\1\s\libraries\Microsoft.Bot.Builder.AI.LUIS\LuisRecognizer.cs:line 444
at Microsoft.Bot.Builder.AI.Luis.LuisRecognizer.RecognizeAsync(ITurnContext turnContext, CancellationToken cancellationToken) in D:\a\1\s\libraries\Microsoft.Bot.Builder.AI.LUIS\LuisRecognizer.cs:line 124Is there a problem or I'm doing something wring?
1 vote -
Increase child item upper limit for list entities
List Entity is advertised as the optimal entity type to use in scenarios where specific terms need to be detected exactly with high accuracy.
Within such scenarios, however, the number of terms under a given category can be extremely high. The current limit of 20,000 child items would be unable to handle such cases. Handling a set of fixed terms may be associated in usages where the margin of error must be minimal, and thus, using other types of entities cannot be considered as a workaround.
As such, an increase in the upper limit is requested.2 votes -
Music domain deleted
There was a Music pre-built domain which has intents like PlayMusic, Decrease/Increase Volume and SkipBack/SkipForward. But this week the entire pre-built domain is gone. When could you bring it back? Thanks!
1 vote -
Numerical entity detected as Datetime by LUIS when using the French language
Hi all,
I notice that simple numerical entity such as 2, 3, 4 have detected as datetime entity , and not only as builtin.number, by LUIS when using the French language.
This behaviour occurs with the API version 2.0, below a JSON answer returned by LUIS as example.
Thanks
{
"query": "station 2",
"topScoringIntent": {"intent": "Station by index",
"score": 0.9843828},
"intents": [
…{
"intent": "Station by index",
"score": 0.9843828
},
{
"intent": "Station by code",
"score": 0.01580255
},
{
"intent": "Inline open Checklist question",
"score": 0.00675197
},
{
"intent": "Scroll down",
"score": 0.006016401
},
{
"intent": "Force answer",2 votes -
Some numbers are not detected by LUIS as number entity when using the Italian language
Hi all,
I would like to highlight some issues about numberical entity identification with the Italian language (API ver 2.0).
Utterances containing numbers such as "uno" (one), 15, 4, sei (six), due (two), have not correctly handled by Microsoft Language Understanding.
The output JSON provided by the cloud service for the examples listed above, does not contain entity (see entities segment below).
Good behaviour example:
{
"query": "stazione due",
"topScoringIntent": {"intent": "Station by index",
"score": 0.9663627},
"intents": [
…{
"intent": "Station by index",
"score": 0.9663627
},
{
"intent": "Station by code",
"score": 0.0247762073
},
{
"intent": "Help",
"score":2 votes -
Utterances accents and punctuation marks validation
I have been working side by side with Partners and Customers in LATAM and I have seen a lot of confusion using utterances in Spanish with the accents and punctuation marks such as the period, question mark, exclamation point, comma, semicolon, colon, dash, hyphen, parentheses, brackets, braces, apostrophe, quotation marks, and ellipsis.
I have seen Alexa Developer Console prevents this kind of characters in some way it reduces the possible errors generated during the training steps.
Is it possible to add a validation directly to the LUIS portal in the Utterances field to prevent and normalize the way training should…
9 votes -
application not found with luis api version 3.0 preview
0
I was testing the new preview 3.0 version for LUIS on the test console available at "https://westus.dev.cognitive.microsoft.com/docs/services/luis-endpoint-api-v3-0-preview/operations/5cb0a9459a1fe8fa44c28dd8/console" .
Despite I am using the same key and app id that correctly work for version 2.0 I get as response the error message "The application wasn't found. Please make sure that the application is published to this region".
The ID for the application I inserted in the console form is published for westus region, the error message seems not truthful.
Anybody else is having the same issue?
Thanks
2 votes -
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 -
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 -
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 -
Persistence of Batch Test Screen
When I got to batch test my document sets, I see the results in the scatter graph, but when I come back say a day later it looks like I am forced to rerun the batch test. Is there a way to persist these scatter graphs? I have a similar request on this forum to export these results in text format.
4 votesHello,
We are currently working on some batch testing APIs, and are working on adding support to the UI as well. The results would be available as JSON.
Thanks,
Luke
- Don't see your idea?