fixing broken bookmark

Author: paulth1

articles/ai-services/language-service/conversational-language-understanding/how-to/build-schema.md

@@ -19,8 +19,8 @@ In conversational language understanding projects, the *schema* is defined as th
 
 Consider the following guidelines when you choose intents for your project:
 
-  - 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*.
-  - 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.
+  - **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*.
+  - **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.
 
 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.
 
@@ -70,7 +70,7 @@ To add a prebuilt component, select the prebuilt type from the dropdown menu in
 
    <!--:::image type="content" source="../media/add-prebuilt-component.png" alt-text="A screenshot that shows a prebuilt component in Language Studio." lightbox="../media/add-prebuilt-component.png":::-->
 
-### Add list component
+### Add a list component
 
 To add a list component, select **Add list**. You can add multiple lists to each entity:
 
@@ -80,7 +80,7 @@ To add a list component, select **Add list**. You can add multiple lists to each
 
    <!--:::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":::-->
 
-### Add regex component
+### Add a regex component
 
 To add a regex component, select **Add expression**. Name the regex key, and enter a regular expression that matches the entity to be extracted.
 

articles/ai-services/language-service/conversational-language-understanding/how-to/create-project.md

@@ -22,10 +22,10 @@ Use this article to learn how to set up these requirements and create a project.
 
 ### Create a Language resource
 
-Before you start using CLU, you need an Azure AI Language resource.
+Before you start using conversational language understanding (CLU), you need an Azure AI Language resource.
 
 > [!NOTE]
-> You need to have an Owner role assigned on the resource group to create a Language resource.
+> You need to have an Owner role assigned for the resource group to create a Language resource.
 
 [!INCLUDE [create a new resource from the Azure portal](../includes/resource-creation-azure-portal.md)]
 

articles/ai-services/language-service/conversational-language-understanding/how-to/migrate-from-luis.md

@@ -41,7 +41,7 @@ The following table presents a side-by-side comparison between the features of L
 |Intents and utterances| Intents and utterances |All intents and utterances are transferred. Utterances are labeled with their transferred entities. |
 |Application GUIDs |Project names| A project is created for each migrating application with the application name. Any special characters in the application names are removed in CLU.|
 |Versioning| Every time you train, a model is created and acts as a version of your [project](#how-do-i-manage-versions-in-clu). | A project is created for the selected application version. |
-|Evaluation using batch testing |Evaluation using testing sets | [Adding your testing dataset](../how-to/tag-utterances.md#how-to-label-your-utterances) is required.|  
+|Evaluation using batch testing |Evaluation using testing sets | [Adding your testing dataset](../how-to/tag-utterances.md#label-your-utterances) is required.|  
 |Role-Based Access Control (RBAC) for LUIS resources |Role-Based Access Control (RBAC) available for Language resources |Language resource RBAC must be [manually added after migration](../../concepts/role-based-access-control.md). |
 |Single training mode| Standard and advanced [training modes](#how-are-the-training-times-different-in-clu-how-is-standard-training-different-from-advanced-training) | Training is required after application migration. |
 |Two publishing slots and version publishing |Ten deployment slots with custom naming | Deployment is required after the application’s migration and training. |

articles/ai-services/language-service/conversational-language-understanding/how-to/tag-utterances.md

@@ -33,7 +33,7 @@ After you [build your schema](build-schema.md) and [create your project](create-
 As you add utterances and label them, keep in mind:
 
 * The machine learning models generalize based on the labeled examples that you provide. The more examples that you provide, the more data points the model has to make better generalizations.
-* The precision, consistency, and completeness of your labeled data are key factors to determining model performance.
+* The precision, consistency, and completeness of your labeled data are key factors to determining model performance:
 
     * **Label precisely:** Label each intent and entity to its right type always. Only include what you want classified and extracted. Avoid unnecessary data in your labels.
     * **Label consistently:** The same entity should have the same label across all the utterances.
@@ -95,7 +95,9 @@ To delete an entity:
 
 ## Suggest utterances with Azure OpenAI
 
-In CLU, use Azure OpenAI to suggest utterances to add to your project by using generative language models. We recommend that you use an Azure AI Foundry resource while you use CLU so that you don't need to connect multiple resources. To use the Azure AI Foundry resource, you need to provide your Azure AI Foundry resource with elevated access. To do so, access the Azure portal. Within your Azure AI resource, provide access as a **Cognitive Services User** to itself. This step ensures that all parts of your resource are communicating correctly.
+In CLU, use Azure OpenAI to suggest utterances to add to your project by using generative language models. We recommend that you use an Azure AI Foundry resource while you use CLU so that you don't need to connect multiple resources. 
+
+To use the Azure AI Foundry resource, you need to provide your Azure AI Foundry resource with elevated access. To do so, access the Azure portal. Within your Azure AI resource, provide access as a **Cognitive Services User** to itself. This step ensures that all parts of your resource are communicating correctly.
 
 ### Connect with separate Language and Azure OpenAI resources
 
@@ -113,13 +115,17 @@ On the **Data labeling** page:
 1. After you select an Azure OpenAI resource, select **Connect** so that your Language resource has direct access to your Azure OpenAI resource. It assigns your Language resource the **Cognitive Services User** role to your Azure OpenAI resource. Now your current Language resource has access to Azure OpenAI. If the connection fails, follow [these steps](#add-required-configurations-to-azure-openai-resource) to manually add the correct role to your Azure OpenAI resource.
 1. After the resource is connected, select the deployment. The model that we recommend for the Azure OpenAI deployment is `gpt-35-turbo-instruct`.
 1. Select the intent for which you want to get suggestions. Make sure the intent that you selected has at least five saved utterances to be enabled for utterance suggestions. The suggestions provided by Azure OpenAI are based on the most recent utterances that you added for that intent.
-1. Select **Generate utterances**. Then the suggested utterances show up with a dotted line around them and the note **Generated by AI**. Those suggestions must be accepted or rejected. Accepting a suggestion adds it to your project, as if you had added it yourself. Rejecting a suggestion deletes it entirely. Only accepted utterances are part of your project and used for training or testing. To accept or reject, select the green check mark or red cancel buttons beside each utterance. You can also use **Accept all** and **Reject all** on the toolbar.
+1. Select **Generate utterances**.
+
+   The suggested utterances show up with a dotted line around them and the note **Generated by AI**. Those suggestions must be accepted or rejected. Accepting a suggestion adds it to your project, as if you had added it yourself. Rejecting a suggestion deletes it entirely. Only accepted utterances are part of your project and used for training or testing.
+
+    To accept or reject, select the green check mark or red cancel buttons beside each utterance. You can also use **Accept all** and **Reject all** on the toolbar.
 
     :::image type="content" source="../media/suggest-utterances.png" alt-text="A screenshot that shows suggested utterances." lightbox="../media/suggest-utterances.png":::
 
-Using this feature entails a charge to your Azure OpenAI resource for a similar number of tokens to the suggested utterances generated. For information on Azure OpenAI pricing, see [Azure OpenAI Service pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/).
+Use of this feature entails a charge to your Azure OpenAI resource for a similar number of tokens to the suggested utterances that are generated. For information on Azure OpenAI pricing, see [Azure OpenAI Service pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/).
 
-### Add required configurations to an Azure OpenAI resource
+### Add required configurations to Azure OpenAI resource
 
 Enable identity management for your Language resource by using the following options.
 

articles/ai-services/language-service/conversational-language-understanding/includes/language-studio/create-project.md

@@ -15,13 +15,13 @@ ms.author: lajanuar
 
     :::image type="content" source="../../media/projects-page.png" alt-text="A screenshot that shows the conversation project page in Language Studio." lightbox="../../media/projects-page.png":::
 
-To create a new project, provide the following information:
+1. To create a new project, provide the following information:
 
-|Value  | Description  |
-|---------|---------|
-|Name     | A name for your project. After you create it, the name can't be changed.  |
-|Description    | Optional project description.        |
-|Utterances primary language     | The primary language of your project. Your training data should primarily be in this language.        |
-|Enable multiple languages    |  Whether you want to enable your project to support [multiple languages](../../language-support.md#multi-lingual-option) at once.       |
+    |Value  | Description  |
+    |---------|---------|
+    |Name     | A name for your project. After you create it, the name can't be changed.  |
+    |Description    | Optional project description.        |
+    |Utterances primary language     | The primary language of your project. Your training data should primarily be in this language.        |
+    |Enable multiple languages    |  Whether you want to enable your project to support [multiple languages](../../language-support.md#multi-lingual-option) at once.       |
 
-After you're finished, select **Create**. You should now see the **Getting started** landing page for your project.
+1. After you're finished, select **Create**. You should now see the **Getting started** landing page for your project.