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
Copy file name to clipboardExpand all lines: articles/ai-services/language-service/conversational-language-understanding/concepts/data-formats.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -17,7 +17,7 @@ If you're uploading your data into conversational language understanding, it mus
17
17
18
18
## Import project file format
19
19
20
-
If you're [importing a project](../how-to/create-project.md#import-project) into conversational language understanding, the file uploaded must be in the following format:
20
+
If you're [importing a project](../how-to/create-project.md#import-a-project) into conversational language understanding, the file uploaded must be in the following format:
21
21
22
22
```json
23
23
{
@@ -175,5 +175,5 @@ Conversational language understanding offers the option to upload your utterance
175
175
176
176
## Related content
177
177
178
-
* For more information on importing your labeled data into your project directly, see [Import project](../how-to/create-project.md#import-project).
178
+
* For more information on importing your labeled data into your project directly, see [Import project](../how-to/create-project.md#import-a-project).
179
179
* For more information about labeling your data, see [Label your utterances in Language Studio](../how-to/tag-utterances.md). After you label your data, you can [train your model](../how-to/train-model.md).
title: How to build a Conversational Language Understanding project schema
2
+
title: Build a Conversational Language Understanding Project Schema
3
3
titleSuffix: Azure AI services
4
-
description: Use this article to start building a Conversational Language Understanding project schema
4
+
description: Use this article to start building a conversational language understanding project schema.
5
5
author: laujan
6
6
manager: nitinme
7
7
ms.service: azure-ai-language
@@ -11,25 +11,24 @@ ms.author: lajanuar
11
11
ms.custom: language-service-clu
12
12
---
13
13
14
-
# How to build your fine-tuning schema
14
+
# Build your fine-tuning schema
15
15
16
-
In conversational language understanding projects, the *schema* is defined as the combination of intents and entities within your project. Schema design is a crucial part of your project's success. When creating a schema, think about which intents and entities should be included in your project.
16
+
In conversational language understanding projects, the *schema* is defined as the combination of intents and entities within your project. Schema design is a crucial part of your project's success. When you create a schema, think about which intents and entities should be included in your project.
17
17
18
18
## Guidelines and recommendations
19
19
20
-
Consider the following guidelines when picking intents for your project:
20
+
Consider the following guidelines when you choose intents for your project:
21
21
22
-
1. Create distinct, separable intents. An intent is best described as action the user wants to perform. Think of the project you're building and identify all the different actions your users may take when interacting with your project. Sending, calling, and canceling are all actions that are best represented as different intents. "Canceling an order" and "canceling an appointment" are similar, with the distinction being *what* they're canceling. Those two actions should be represented under the same intent, *Cancel*.
22
+
-**Create distinct, separable intents.** An intent is best described as action that the user wants to perform. Think of the project you're building and identify all the different actions that your users might take when they interact with your project. Sending, calling, and canceling are all actions that are best represented as different intents. "Canceling an order" and "canceling an appointment" are similar, with the distinction being *what* they're canceling. Those two actions should be represented under the same intent, *cancel*.
23
+
-**Create entities to extract relevant pieces of information within your text.** The entities should be used to capture the relevant information that's needed to fulfill your user's action. For example, *order* or *appointment* could be different things that a user is trying to cancel, and you should create an entity to capture that piece of information.
23
24
24
-
1. Create entities to extract relevant pieces of information within your text. The entities should be used to capture the relevant information needed to fulfill your user's action. For example, *order* or *appointment* could be different things a user is trying to cancel, and you should create an entity to capture that piece of information.
25
+
You can "send a message," "send an email," or "send a package." Creating an intent to capture each of those requirements won't scale over time, and you should use entities to identify *what* the user was sending. The combination of intents and entities should determine your conversation flow.
25
26
26
-
You can *"send"* a *message*, *"send"* an *email*, or *"send"* a package. Creating an intent to capture each of those requirements won't scale over time, and you should use entities to identify *what* the user was sending. The combination of intents and entities should determine your conversation flow.
27
+
For example, consider a company where the bot developers identified the three most common actions that their users take when they use a calendar:
27
28
28
-
For example, consider a company where the bot developers identified the three most common actions their users take when using a calendar:
29
-
30
-
* Setup new meetings
31
-
* Respond to meeting requests
32
-
* Cancel meetings
29
+
* Set up new meetings.
30
+
* Respond to meeting requests.
31
+
* Cancel meetings.
33
32
34
33
They might create an intent to represent each of these actions. They might also include entities to help complete these actions, such as:
35
34
@@ -41,61 +40,58 @@ They might create an intent to represent each of these actions. They might also
41
40
42
41
To build a project schema within [AI Foundry](https://ai.azure.com/?cid=learnDocs):
43
42
44
-
1. Select **Define schema** from the left side menu.
45
-
46
-
1. From the top pivots, you can change the view to be **Intents** or **Entities**.
43
+
1. On the left pane, select **Define schema**.
47
44
48
-
1.To create an intent, select **+ Add intent**. You're prompted to type in names and descriptions for as many intents as you'd like to create. Descriptions are only required for using Quick Deploy to help Azure OpenAI better understand the context of your intents.
45
+
1.Select the **Intents** or **Entities** tabs.
49
46
50
-
1.Repeat the steps to develop intents that encompass all the actions the user is likely to perform while interacting with the project.
47
+
1.To create an intent, select **+ Add intent**. You're prompted to enter names and descriptions for as many intents as you want to create. Descriptions are required only for using the **Quick Deploy** option to help Azure OpenAI better understand the context of your intents.
51
48
49
+
1. Repeat the steps to develop intents that encompass all the actions that the user is likely to perform while interacting with the project.
52
50
51
+
:::image type="content" source="../media/build-schema-page.png" alt-text="A screenshot that shows the schema creation page for conversation projects in Language Studio." lightbox="../media/build-schema-page.png":::
53
52
54
-
:::image type="content" source="../media/build-schema-page.png" alt-text="A screenshot showing the schema creation page for conversation projects in Language Studio." lightbox="../media/build-schema-page.png":::
55
-
56
-
1. If you'd like to continue with [data labeling](tag-utterances.md) and advanced training a custom `CLU` model, you can select **Manage data** from the left side menu to add examples for intents and label them with entities, if desired.
53
+
1. If you want to continue with [data labeling](tag-utterances.md) and advanced training a custom `CLU` model, on the left pane, select **Manage data** to add examples for intents and label them with entities, if desired.
57
54
58
55
## Add entities
59
56
60
-
1.Move to**Entities**pivot from the top of the page.
57
+
1.Select the**Entities**tab.
61
58
62
-
1. To add an entity, select **+ Add entity** from the top. You're prompted to type in a name to create the entity.
59
+
1. To add an entity, select **+ Add entity**. You're prompted to enter a name to create the entity.
63
60
64
-
1. After creating an entity, you can select the entity name to change the **Entity components** type. Multiple components—learned, list, regex, or prebuilt—define every entity. A learned component is added to all your entities once you label them in your utterances.
61
+
1. After you create an entity, you can select the entity name to change the **Entity components** type. Multiple components like learned, list, regex, or prebuilt are used to define every entity. A learned component is added to all your entities after you label them in your utterances.
65
62
66
-
:::image type="content" source="../media/entity-details.png" alt-text="A screenshot showing the entity details page for conversation projects in Language Studio." lightbox="../media/entity-details.png":::
63
+
:::image type="content" source="../media/entity-details.png" alt-text="A screenshot that shows the Entity components page for conversation projects in Language Studio." lightbox="../media/entity-details.png":::
67
64
68
65
1. You can also add a [list](../concepts/entity-components.md#list-component), [regex](../concepts/entity-components.md#regex-component), or [prebuilt](../concepts/entity-components.md#prebuilt-component) component to each entity.
69
66
70
-
### Add prebuilt component
67
+
### Add a prebuilt component
71
68
72
-
To add a **prebuilt** component, select the prebuilt type from the drop-down menu in the Entity options section.
69
+
To add a prebuilt component, select the prebuilt type from the dropdown menu in the **Entity options** section.
73
70
74
-
<!--:::image type="content" source="../media/add-prebuilt-component.png" alt-text="A screenshot showing a prebuilt-component in Language Studio." lightbox="../media/add-prebuilt-component.png":::-->
71
+
<!--:::image type="content" source="../media/add-prebuilt-component.png" alt-text="A screenshot that shows a prebuiltcomponent in Language Studio." lightbox="../media/add-prebuilt-component.png":::-->
75
72
76
-
### Add list component
73
+
### Add a list component
77
74
78
-
To add a **list** component, select **Add list**. You can add multiple lists to each entity:
75
+
To add a list component, select **Add list**. You can add multiple lists to each entity:
79
76
80
-
1. Create a new list, in the *List key* text box, enter the normalized value that is returned when any of the synonyms values is extracted.
77
+
1. Create a new list, and in the **List key** text box, enter the normalized value that was returned when any of the synonyms values were extracted.
81
78
82
-
1.Start typing in your synonyms and hit enter after each one. We recommend having a synonym list in multiple languages.
79
+
1.Enter your synonyms and select Enter after each one. We recommend having a synonym list in multiple languages.
83
80
84
-
<!--:::image type="content" source="../media/add-list-component.png" alt-text="A screenshot showing a list component in Language Studio." lightbox="../media/add-list-component.png":::-->
81
+
<!--:::image type="content" source="../media/add-list-component.png" alt-text="A screenshot that shows a list component in Language Studio." lightbox="../media/add-list-component.png":::-->
85
82
86
-
### Add regex component
83
+
### Add a regex component
87
84
88
-
To add a regex component, select Add expression. Name the regex key and type a regular expression that matches the entity to be extracted.
85
+
To add a regex component, select **Add expression**. Name the regex key, and enter a regular expression that matches the entity to be extracted.
89
86
90
87
### Define entity options
91
88
92
-
Change to the **Entity options** pivot in the entity details page. When multiple components are defined for an entity, their predictions may overlap. When an overlap occurs, each entity's final prediction is determined based on the [entity option](../concepts/entity-components.md#entity-options) you select in this step. Select the one that you want to apply to this entity and select the **Save** button.
93
-
94
-
<!--:::image type="content" source="../media/entity-options.png" alt-text="A screenshot showing an entity option in Language Studio." lightbox="../media/entity-options.png":::-->
89
+
Select the **Entity Options** tab on the entity details page. When multiple components are defined for an entity, their predictions might overlap. When an overlap occurs, each entity's final prediction is determined based on the [entity option](../concepts/entity-components.md#entity-options) that you select in this step. Select the option that you want to apply to this entity, and then select **Save**.
95
90
91
+
<!--:::image type="content" source="../media/entity-options.png" alt-text="A screenshot that shows an entity option in Language Studio." lightbox="../media/entity-options.png":::-->
96
92
97
-
After you create your entities, you can come back and edit them. You can **edit entity components** or **delete** them by selecting this option from the top menu.
93
+
After you create your entities, you can come back and edit them. You can edit entity components or delete them by selecting **Edit** or **Delete**.
98
94
99
-
## Next Steps
95
+
## Related content
100
96
101
97
*[Add utterances and label your data](tag-utterances.md)
title: How to create projects in Conversational Language Understanding
2
+
title: Create Projects in Conversational Language Understanding
3
3
titleSuffix: Azure AI services
4
-
description: Use this article to learn how to create projects in Conversational Language Understanding.
4
+
description: This article shows you how to create projects in conversational language understanding (CLU).
5
5
author: laujan
6
6
manager: nitinme
7
7
ms.service: azure-ai-language
@@ -11,36 +11,33 @@ ms.author: lajanuar
11
11
ms.custom: language-service-clu
12
12
---
13
13
14
-
# How to create a CLU fine-tuning task
14
+
# Create a CLU fine-tuning task
15
15
16
-
Use this article to learn how to set up these requirements and create a project.
16
+
Use this article to learn how to set up these requirements and create a project.
17
17
18
18
## Prerequisites
19
19
20
-
Before you start using CLU, you will need a few items:
20
+
* An Azure subscription. If you don't have one, you can [create one for free](https://azure.microsoft.com/free/cognitive-services).
21
+
* An Azure AI Language resource.
21
22
22
-
* An Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services).
23
-
* An Azure AI Language resource
23
+
### Create a Language resource
24
24
25
-
### Create a Language resource
26
-
27
-
Before you start using CLU, you will need an Azure AI Language resource.
25
+
Before you start using conversational language understanding (CLU), you need an Azure AI Language resource.
28
26
29
27
> [!NOTE]
30
-
> *You need to have an **owner** role assigned on the resource group to create a Language resource.
28
+
> You need to have an Owner role assigned for the resource group to create a Language resource.
31
29
32
30
[!INCLUDE [create a new resource from the Azure portal](../includes/resource-creation-azure-portal.md)]
33
31
34
32
[!INCLUDE [create a new resource from Language Studio](../includes/resource-creation-language-studio.md)]
35
33
36
-
37
34
## Sign in to Language Studio
38
35
39
36
[!INCLUDE [Sign in to Language studio](../includes/language-studio/sign-in-studio.md)]
40
37
41
38
## Create a conversation project
42
39
43
-
Once you have a Language resource created, create a Conversational Language Understanding project.
40
+
After you create a Language resource, create a CLU project.
44
41
45
42
### [Azure AI Foundry](#tab/azure-ai-foundry)
46
43
@@ -52,39 +49,39 @@ Once you have a Language resource created, create a Conversational Language Unde
52
49
53
50
---
54
51
55
-
## Import project
52
+
## Import a project
56
53
57
54
### [Azure AI Foundry](#tab/azure-ai-foundry)
58
55
59
-
You can export a Conversational Language Understanding project as a JSON file at any time by going to the conversation projects page, selecting a project, and from the top menu, clicking on**Export**.
56
+
You can export a CLU project as a JSON file at any time. On the conversation projects page, select a project, and on the top menu, select**Export**.
60
57
61
-
:::image type="content" source="../media/export.png" alt-text="A screenshot showing the Conversational Language Understanding export button." lightbox="../media/export.png":::
58
+
:::image type="content" source="../media/export.png" alt-text="A screenshot that shows the CLU Export button." lightbox="../media/export.png":::
62
59
63
-
That project can be reimported as a new project. If you import a project with the exact same name, it replaces the project's data with the newly imported project's data.
60
+
You can reimport that project as a new project. If you import a project with the exact same name, it replaces the project's data with the newly imported project's data.
64
61
65
-
If you have an existing LUIS application, you can _import_ the LUIS application JSON to Conversational Language Understanding directly, and it will create a Conversation project with all the pieces that are currently available: Intents, ML entities, and utterances. See [the LUIS migration article](../how-to/migrate-from-luis.md) for more information.
62
+
If you have an existing Language Understanding (LUIS) application, you can _import_ the LUIS application JSON to CLU directly. It creates a Conversation project with all the pieces that are currently available: intents, machine learning entities, and utterances. For more information, see [Migrate from Language Understanding (LUIS) to conversational language understanding (CLU)](../how-to/migrate-from-luis.md).
66
63
67
-
To import a project, select the arrow button next to **Create a new project** and select **Import**, then select the LUIS or Conversational Language Understanding JSON file.
64
+
To import a project, select the arrow button next to **Create a new project** and select **Import**. Then select the LUIS or CLU JSON file.
68
65
69
-
:::image type="content" source="../media/import.png" alt-text="A screenshot showing the Conversational Language Understanding import button." lightbox="../media/import.png":::
66
+
:::image type="content" source="../media/import.png" alt-text="A screenshot that shows the CLU Import button." lightbox="../media/import.png":::
You can export a Conversational Language Understanding project as a JSON file at any time by going to the conversation projects page, selecting a project, and pressing**Export**.
80
+
You can export a CLU project as a JSON file at any time. On the conversation projects page, select a project, and then select**Export**.
84
81
85
82
### [REST APIs](#tab/rest-api)
86
83
87
-
You can export a Conversational Language Understanding project as a JSON file at any time.
84
+
You can export a CLU project as a JSON file at any time.
0 commit comments