Merge pull request #109678 from diberry/diberry/0330-luis-fresh-2

[Cogsvs] LUIS - fresh 2 - roles tutorial

Author: v-shils

articles/cognitive-services/LUIS/luis-tutorial-composite-entity.md

@@ -1,16 +1,8 @@
 ---
 title: "Tutorial: Composite entity tutorial - LUIS"
-titleSuffix: Azure Cognitive Services
 description: In this tutorial, add a composite entity to bundle extracted data of various types into a single containing entity. By bundling the data, the client application can easily extract related data in different data types.
-services: cognitive-services
-author: diberry
-manager: nitinme
-ms.custom: seodec18
-ms.service: cognitive-services
-ms.subservice: language-understanding
 ms.topic: tutorial
-ms.date: 12/17/2019
-ms.author: diberry
+ms.date: 03/31/2020
 ---
 
 # Tutorial: Group and extract related data
@@ -103,11 +95,11 @@ LUIS provides several prebuilt entities for common data extraction.
 
 ## Train the app so the changes to the intent can be tested
 
-[!INCLUDE [LUIS How to Train steps](../../../includes/cognitive-services-luis-tutorial-how-to-train.md)]
+To train the app, select **Train**. Training applies the changes, such as the new entities and the labeled utterances, to the active model.
 
-## Publish the app so the trained model is queryable from the endpoint
+## Publish the app to access it from the HTTP endpoint
 
-[!INCLUDE [LUIS How to Publish steps](../../../includes/cognitive-services-luis-tutorial-how-to-publish.md)]
+[!INCLUDE [LUIS How to Publish steps](includes/howto-publish.md)]
 
 ## Get intent and entity prediction from endpoint
 
@@ -181,9 +173,7 @@ LUIS provides several prebuilt entities for common data extraction.
 
    This utterance returns a composite entities array. Each entity is given a type and value. To find more precision for each child entity, use the combination of type and value from the composite array item to find the corresponding item in the entities array.
 
-## Clean up resources
-
-[!INCLUDE [LUIS How to clean up resources](../../../includes/cognitive-services-luis-tutorial-how-to-clean-up-resources.md)]
+[!INCLUDE [LUIS How to clean up resources](includes/quickstart-tutorial-cleanup-resources.md)]
 
 ## Related information
 

articles/cognitive-services/LUIS/tutorial-entity-roles.md

@@ -1,22 +1,14 @@
 ---
 title: "Tutorial: Contextual data with roles - LUIS"
-titleSuffix: Azure Cognitive Services
 description: Find related data based on context. For example, an origin and destination locations for a physical move from one building and office to another building and office are related.
-services: cognitive-services
-author: diberry
-manager: nitinme
-ms.custom: seodec18
-ms.service: cognitive-services
-ms.subservice: language-understanding
 ms.topic: tutorial
-ms.date: 12/17/2019
-ms.author: diberry
+ms.date: 03/30/2020
 #Customer intent: As a new user, I want to understand how and why to use roles on an entity.
 ---
 
 # Tutorial: Extract contextually related data from an utterance
 
-In this tutorial, find related pieces of data based on context. For example, an origin and destination locations for a transfer from one city to another. Both pieces of data may be required and they are related to each other.
+In this tutorial, find related pieces of data based on context. For example, origin and destination locations for a transfer from one city to another. Both pieces of data may be required and they are related to each other.
 
 A role can be used with any prebuilt or custom entity type, and used in both example utterances and patterns.
 
@@ -45,24 +37,26 @@ A role should be used when the entity data to extract:
 
 ## Create a new app
 
-1. Sign in to the preview LUIS portal with the URL of [https://preview.luis.ai](https://preview.luis.ai).
+1. Sign in to the [LUIS **preview** portal](https://preview.luis.ai).
 
-1. Select **Create new app**, enter the name `HumanResources` and keep the default culture, **English**. Leave the description empty.
-
-1. Select **Done**.
+1. Select **+ New app for conversation**, enter the name `HumanResources` and keep the default culture, **English**. Leave the description and prediction resource empty. Select **Done**.
 
 ## Create an intent to move employees between cities
 
+An intent is used to classify user utterances based on the user's intention, determined from the natural language text.
+
+In order to classify an utterance, the intent needs examples of user utterances that should be classified with this intent.
+
 1. [!INCLUDE [Start in Build section](../../../includes/cognitive-services-luis-tutorial-build-section.md)]
 
-1. Select **Create new intent**.
+1. Select **+ Create**.
 
 1. Enter `MoveEmployeeToCity` in the pop-up dialog box then select **Done**.
 
     > [!div class="mx-imgBorder"]
     > ![Screenshot of create new intent dialog with](./media/tutorial-entity-roles/create-new-intent-move-employee-to-city.png)
 
-1. Add example utterances to the intent.
+1. Add several example utterances to this intent that you expect a user to ask.
 
     |Example utterances|
     |--|
@@ -81,24 +75,29 @@ A role should be used when the entity data to extract:
 
 ## Add prebuilt entity geographyV2
 
-The prebuilt entity, geographyV2, extracts location information, including city names. Since the utterances have two city names, relating to each other in context, use roles to extract that context.
+The prebuilt entity, **geographyV2**, extracts location information, including city names. Since the utterances have two city names, relating to each other in context, use roles to extract that context.
 
 1. Select **Entities** from the left-side navigation.
 
-1. Select **Add prebuilt entity**, then select `geo` in the search bar to filter the prebuilt entities.
+1. Select **+ Add prebuilt entity**, then enter `geo` in the search bar to filter the prebuilt entities.
 
     > [!div class="mx-imgBorder"]
     > ![Add geographyV2 prebuilt entity to app](media/tutorial-entity-roles/add-geographyV2-prebuilt-entity.png)
 
 1. Select the checkbox and select **Done**.
+
+## Add roles to prebuilt entity
+
 1. In the **Entities** list, select the **geographyV2** to open the new entity.
-1. Add two roles, `Origin`, and `Destination`.
+1. To add a role, select **+** and add the following two roles: `Origin`, and `Destination`.
 
     > [!div class="mx-imgBorder"]
     > ![Add roles to prebuilt entity](media/tutorial-entity-roles/add-roles-to-prebuilt-entity.png)
 
+## Label entity roles in example utterances
+
 1. Select **Intents** from the left-side navigation, then select the **MoveEmployeeToCity** intent. Notice the city names are labeled with the prebuilt entity **geographyV2**.
-1. In the context toolbar, select the **Entity palette**.
+1. In the context toolbar, select the **Entity palette** with the _pencil icon_.
 
     > [!div class="mx-imgBorder"]
     > ![Select Entity Palette from content toolbar](media/tutorial-entity-roles/intent-detail-context-toolbar-select-entity-palette.png)
@@ -118,18 +117,21 @@ The prebuilt entity, geographyV2, extracts location information, including city
 
 ## Train the app so the changes to the intent can be tested
 
-[!INCLUDE [LUIS How to Train steps](../../../includes/cognitive-services-luis-tutorial-how-to-train.md)]
+To train the app, select **Train**. Training applies the changes, such as the new entities and the labeled utterances, to the active model.
+
+## Publish the app to access it from the HTTP endpoint
 
-## Publish the app so the trained model is queryable from the endpoint
+[!INCLUDE [LUIS How to Publish steps](includes/howto-publish.md)]
 
-[!INCLUDE [LUIS How to Publish steps](../../../includes/cognitive-services-luis-tutorial-how-to-publish.md)]
 
 ## Get intent and entity prediction from endpoint
 
-1. [!INCLUDE [LUIS How to get endpoint first step](../../../includes/cognitive-services-luis-tutorial-how-to-get-endpoint.md)]
+1. [!INCLUDE [LUIS How to get endpoint first step](includes/howto-get-endpoint.md)]
 
 
-1. Go to the end of the URL in the address bar and enter `Please move Carl Chamerlin from Tampa to Portland`. The last querystring parameter is `q`, the utterance **query**. This utterance is not the same as any of the labeled utterances so it is a good test and should return the `MoveEmployee` intent with the entity extracted.
+1. Go to the end of the URL in the address bar and replace _YOUR_QUERY_HERE_ with `Please move Carl Chamerlin from Tampa to Portland`.
+
+This utterance is not the same as any of the labeled utterances so it is a good test and should return the `MoveEmployee` intent with the entity extracted.
 
     ```json
     {
@@ -169,9 +171,7 @@ The prebuilt entity, geographyV2, extracts location information, including city
 
     The correct intent is predicted and the entities array has both the origin and destination roles in the corresponding **entities** property.
 
-## Clean up resources
-
-[!INCLUDE [LUIS How to clean up resources](../../../includes/cognitive-services-luis-tutorial-how-to-clean-up-resources.md)]
+[!INCLUDE [LUIS How to clean up resources](includes/quickstart-tutorial-cleanup-resources.md)]
 
 ## Related information
 

articles/cognitive-services/LUIS/tutorial-machine-learned-entity.md

@@ -2,7 +2,7 @@
 title: "Tutorial: extract structured data with machine-learned entity - LUIS"
 description: Extract structured data from an utterance using the machine-learned entity. To increase the extraction accuracy, add subcomponents with descriptors and constraints.
 ms.topic: tutorial
-ms.date: 03/30/2020
+ms.date: 03/31/2020
 #Customer intent: As a new user, I want to understand how to extract complex data contained in a user utterance.
 ---
 
@@ -211,7 +211,7 @@ Test the app using the interactive **Test** panel. This process lets you enter a
 
 1. [!INCLUDE [LUIS How to get endpoint first step](includes/howto-get-endpoint.md)]
 
-1. Go to the end of the URL in the address and enter the same query as you entered in the interactive test panel.
+1. Go to the end of the URL in the address and replace _YOUR_QUERY_HERE_ with the same query as you entered in the interactive test panel.
 
     `deliver a medium veggie pizza`