You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
*[Suggest endpoint queries for entities](https://westus.dev.cognitive.microsoft.com/docs/services/luis-programmatic-apis-v3-0-preview/operations/5890b47c39e2bb052c5b9c2e)
37
-
*[Suggest endpoint queries for intents](https://westus.dev.cognitive.microsoft.com/docs/services/luis-programmatic-apis-v3-0-preview/operations/5890b47c39e2bb052c5b9c2d)
38
-
33
+
* Add label
34
+
* Add batch label
35
+
* Review labels
36
+
* Suggest endpoint queries for entities
37
+
* Suggest endpoint queries for intents
38
+
For more information, see the [LUIS reference documentation](/rest/api/cognitiveservices-luis/authoring/features?view=rest-cognitiveservices-luis-authoring-v3.0-preview&tabs=HTTP&preserve-view=true).
Copy file name to clipboardExpand all lines: articles/ai-services/LUIS/concepts/utterances.md
+14-14Lines changed: 14 additions & 14 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -33,17 +33,17 @@ When you start [adding example utterances](../how-to/entities.md) to your LUIS
33
33
34
34
## Utterances aren't always well formed
35
35
36
-
Your app may need to process sentences, like "Book a ticket to Paris for me", or a fragment of a sentence, like "Booking" or "Paris flight" Users also often make spelling mistakes. When planning your app, consider whether or not you want to use [Bing Spell Check](../luis-tutorial-bing-spellcheck.md) to correct user input before passing it to LUIS.
36
+
Your app might need to process sentences, like "Book a ticket to Paris for me," or a fragment of a sentence, like "Booking" or "Paris flight" Users also often make spelling mistakes. When planning your app, consider whether or not you want to use [Bing Spell Check](../luis-tutorial-bing-spellcheck.md) to correct user input before passing it to LUIS.
37
37
38
-
If you do not spell check user utterances, you should train LUIS on utterances that include typos and misspellings.
38
+
If you don't spell check user utterances, you should train LUIS on utterances that include typos and misspellings.
39
39
40
40
### Use the representative language of the user
41
41
42
-
When choosing utterances, be aware that what you think are common terms or phrases might not be common for the typical user of your client application. They may not have domain experience or use different terminology. Be careful when using terms or phrases that a user would only say if they were an expert.
42
+
When choosing utterances, be aware that what you think are common terms or phrases might not be common for the typical user of your client application. They might not have domain experience or use different terminology. Be careful when using terms or phrases that a user would only say if they were an expert.
43
43
44
44
### Choose varied terminology and phrasing
45
45
46
-
You will find that even if you make efforts to create varied sentence patterns, you will still repeat some vocabulary. For example, the following utterances have similar meaning, but different terminology and phrasing:
46
+
You'll find that even if you make efforts to create varied sentence patterns, you'll still repeat some vocabulary. For example, the following utterances have similar meaning, but different terminology and phrasing:
47
47
48
48
* "*How do I get a computer?*"
49
49
* "*Where do I get a computer?*"
@@ -54,15 +54,15 @@ The core term here, _computer_, isn't varied. Use alternatives such as desktop c
54
54
55
55
## Example utterances in each intent
56
56
57
-
Each intent needs to have example utterances - at least 15. If you have an intent that does not have any example utterances, you will not be able to train LUIS. If you have an intent with one or few example utterances, LUIS may not accurately predict the intent.
57
+
Each intent needs to have example utterances - at least 15. If you have an intent that doesn't have any example utterances, you will not be able to train LUIS. If you have an intent with one or few example utterances, LUIS might not accurately predict the intent.
58
58
59
59
## Add small groups of utterances
60
60
61
61
Each time you iterate on your model to improve it, don't add large quantities of utterances. Consider adding utterances in quantities of 15. Then [Train](../how-to/train-test.md), [publish](../how-to/publish.md), and [test](../how-to/train-test.md) again.
62
62
63
63
LUIS builds effective models with utterances that are carefully selected by the LUIS model author. Adding too many utterances isn't valuable because it introduces confusion.
64
64
65
-
It is better to start with a few utterances, then [review the endpoint utterances](../how-to/improve-application.md) for correct intent prediction and entity extraction.
65
+
It's better to start with a few utterances, then [review the endpoint utterances](../how-to/improve-application.md) for correct intent prediction and entity extraction.
66
66
67
67
## Utterance normalization
68
68
@@ -78,7 +78,7 @@ If you turn on a normalization setting, scores in the **Test** pane, batch tes
78
78
79
79
When you clone a version in the LUIS portal, the version settings are kept in the new cloned version.
80
80
81
-
Set your app's version settings using the LUIS portal by selecting **Manage** from the top navigation menu, in the **Application Settings** page. You can also use the [Update Version Settings API](https://westus.dev.cognitive.microsoft.com/docs/services/5890b47c39e2bb17b84a55ff/operations/versions-update-application-version-settings). See the [Reference](../luis-reference-application-settings.md) documentation for more information.
81
+
Set your app's version settings using the LUIS portal by selecting **Manage** from the top navigation menu, in the **Application Settings** page. You can also use the [Update Version Settings API](/rest/api/cognitiveservices-luis/authoring/versions/update?view=rest-cognitiveservices-luis-authoring-v3.0-preview&tabs=HTTP&preserve-view=true). See the [Reference](../luis-reference-application-settings.md) documentation for more information.
82
82
83
83
## Word forms
84
84
@@ -94,9 +94,9 @@ Diacritics are marks or signs within the text, such as:
94
94
95
95
Normalizing **punctuation** means that before your models get trained and before your endpoint queries get predicted, punctuation will be removed from the utterances.
96
96
97
-
Punctuation is a separate token in LUIS. An utterance that contains a period at the end is a separate utterance than one that does not contain a period at the end, and may get two different predictions.
97
+
Punctuation is a separate token in LUIS. An utterance that contains a period at the end is a separate utterance than one that doesn't contain a period at the end, and might get two different predictions.
98
98
99
-
If punctuation is not normalized, LUIS doesn't ignore punctuation marks by default because some client applications may place significance on these marks. Make sure to include example utterances that use punctuation, and ones that don't, for both styles to return the same relative scores.
99
+
If punctuation isn't normalized, LUIS doesn't ignore punctuation marks by default because some client applications might place significance on these marks. Make sure to include example utterances that use punctuation, and ones that don't, for both styles to return the same relative scores.
100
100
101
101
Make sure the model handles punctuation either in the example utterances (both having and not having punctuation) or in [patterns](../concepts/patterns-features.md) where it is easier to ignore punctuation. For example: I am applying for the {Job} position[.]
102
102
@@ -108,11 +108,11 @@ If you want to ignore specific words or punctuation in patterns, use a [pattern]
108
108
109
109
## Training with all utterances
110
110
111
-
Training is generally non-deterministic: utterance prediction can vary slightly across versions or apps. You can remove non-deterministic training by updating the [version settings](https://westus.dev.cognitive.microsoft.com/docs/services/5890b47c39e2bb17b84a55ff/operations/versions-update-application-version-settings) API with the UseAllTrainingData name/value pair to use all training data.
111
+
Training is nondeterministic: utterance prediction can vary slightly across versions or apps. You can remove nondeterministic training by updating the [version settings](/rest/api/cognitiveservices-luis/authoring/settings/update?view=rest-cognitiveservices-luis-authoring-v3.0-preview&tabs=HTTP&preserve-view=true) API with the UseAllTrainingData name/value pair to use all training data.
112
112
113
113
## Testing utterances
114
114
115
-
Developers should start testing their LUIS application with real data by sending utterances to the [prediction endpoint](../luis-how-to-azure-subscription.md) URL. These utterances are used to improve the performance of the intents and entities with [Review utterances](../how-to/improve-application.md). Tests submitted using the testing pane in the LUIS portal are not sent through the endpoint, and don't contribute to active learning.
115
+
Developers should start testing their LUIS application with real data by sending utterances to the [prediction endpoint](../luis-how-to-azure-subscription.md) URL. These utterances are used to improve the performance of the intents and entities with [Review utterances](../how-to/improve-application.md). Tests submitted using the testing pane in the LUIS portal aren't sent through the endpoint, and don't contribute to active learning.
116
116
117
117
## Review utterances
118
118
@@ -122,10 +122,10 @@ After your model is trained, published, and receiving [endpoint](../luis-glossar
122
122
123
123
### Label for word meaning
124
124
125
-
If the word choice or word arrangement is the same, but doesn't mean the same thing, do not label it with the entity.
125
+
If the word choice or word arrangement is the same, but doesn't mean the same thing, don't label it with the entity.
126
126
127
127
In the following utterances, the word fair is a homograph, which means it's spelled the same but has a different meaning:
128
-
* "*What kind of county fairs are happening in the Seattle area this summer?*"
128
+
* "*What kinds of county fairs are happening in the Seattle area this summer?*"
129
129
* "*Is the current 2-star rating for the restaurant fair?*
130
130
131
131
If you want an event entity to find all event data, label the word fair in the first utterance, but not in the second.
@@ -138,7 +138,7 @@ LUIS expects variations in an intent's utterances. The utterances can vary while
138
138
| Don't use the same format | Do use varying formats |
139
139
|--|--|
140
140
| Buy a ticket to Seattle|Buy 1 ticket to Seattle|
141
-
|Buy a ticket to Paris|Reserve two seats on the red eye to Paris next Monday|
141
+
|Buy a ticket to Paris|Reserve two tickets on the red eye to Paris next Monday|
142
142
|Buy a ticket to Orlando |I would like to book 3 tickets to Orlando for spring break |
LUIS has little or no knowledge of the broader _NLP_ aspects, such as semantic similarity, without explicit identification in examples. For example, the following tokens (words) are three different things until they are used in similar contexts in the examples provided:
33
+
LUIS has little or no knowledge of the broader _NLP_ aspects, such as semantic similarity, without explicit identification in examples. For example, the following tokens (words) are three different things until they're used in similar contexts in the examples provided:
34
34
35
35
* Buy
36
36
* Buying
37
37
* Bought
38
38
39
-
For semantic similarity Natural Language Understanding (NLU), you can use [Conversation Language Understanding](../language-service/conversational-language-understanding/overview.md)
39
+
For semantic similarity Natural Language Understanding (NLU), you can use [Conversation Language Understanding](../language-service/conversational-language-understanding/overview.md).
40
40
41
41
## What are the Authoring and prediction pricing?
42
-
Language Understand has separate resources, one type for authoring, and one type for querying the prediction endpoint, each has their own pricing. See [Resource usage and limits](luis-limits.md#resource-usage-and-limits)
42
+
Language Understand has separate resources, one type for authoring, and one type for querying the prediction endpoint, each has their own pricing. See [Resource usage and limits](luis-limits.md#resource-usage-and-limits).
43
43
44
44
## What are the supported regions?
45
45
46
-
See [region support](https://azure.microsoft.com/global-infrastructure/services/?products=cognitive-services)
46
+
See [region support](https://azure.microsoft.com/global-infrastructure/services/?products=cognitive-services).
47
47
48
48
## How does LUIS store data?
49
49
50
-
LUIS stores data encrypted in an Azure data store corresponding to the region specified by the key. Data used to train the model such as entities, intents, and utterances will be saved in LUIS for the lifetime of the application. If an owner or contributor deletes the app, this data will be deleted with it. If an application hasn't been used in 90 days, it will be deleted.See [Data retention](luis-concept-data-storage.md)to know more details about data storage
50
+
LUIS stores data encrypted in an Azure data store corresponding to the region specified by the key. Data used to train the model such as entities, intents, and utterances will be saved in LUIS for the lifetime of the application. If an owner or contributor deletes the app, this data will be deleted with it. If an application hasn't been used in 90 days, it will be deleted.See [Data retention](luis-concept-data-storage.md)for more details about data storage.
51
51
52
52
## Does LUIS support Customer-Managed Keys (CMK)?
53
53
@@ -71,7 +71,7 @@ Use one of the following solutions:
71
71
72
72
## Why is my app is getting different scores every time I train?
73
73
74
-
Enable or disable the use non-deterministic training option. When disabled, training will use all available data. When enabled (by default), training will use a random sample each time the app is trained, to be used as a negative for the intent. To make sure that you are getting same scores every time, make sure you train your LUIS app with all your data. See the [training article](how-to/train-test.md#change-deterministic-training-settings-using-the-version-settings-api) for more information.
74
+
Enable or disable the use nondeterministic training option. When disabled, training will use all available data. When enabled (by default), training will use a random sample each time the app is trained, to be used as a negative for the intent. To make sure that you are getting same scores every time, make sure you train your LUIS app with all your data. See the [training article](how-to/train-test.md#change-deterministic-training-settings-using-the-version-settings-api) for more information.
75
75
76
76
## I received an HTTP 403 error status code. How do I fix it? Can I handle more requests per second?
77
77
@@ -115,7 +115,7 @@ To get the same top intent between all the apps, make sure the intent prediction
115
115
116
116
When training these apps, make sure to [train with all data](how-to/train-test.md).
117
117
118
-
Designate a single main app. Any utterances that are suggested for review should be added to the main app, then moved back to all the other apps. This is either a full export of the app, or loading the labeled utterances from the main app to the other apps. Loading can be done from either the [LUIS](./luis-reference-regions.md) website or the authoring API for a [single utterance](https://westus.dev.cognitive.microsoft.com/docs/services/5890b47c39e2bb17b84a55ff/operations/5890b47c39e2bb052c5b9c08) or for a [batch](https://westus.dev.cognitive.microsoft.com/docs/services/5890b47c39e2bb17b84a55ff/operations/5890b47c39e2bb052c5b9c09).
118
+
Designate a single main app. Any utterances that are suggested for review should be added to the main app, then moved back to all the other apps. This is either a full export of the app, or loading the labeled utterances from the main app to the other apps. Loading can be done from either the [LUIS](./luis-reference-regions.md?view=rest-cognitiveservices-luis-authoring-v3.0-preview&tabs=HTTP&preserve-view=true) website or the authoring API for a [single utterance](/rest/api/cognitiveservices-luis/authoring/examples/add) or for a [batch](/rest/api/cognitiveservices-luis/authoring/examples/batch?view=rest-cognitiveservices-luis-authoring-v3.0-preview&tabs=HTTP&preserve-view=true).
119
119
120
120
Schedule a periodic review, such as every two weeks, of [endpoint utterances](how-to/improve-application.md) for active learning, then retrain and republish the app.
0 commit comments