Merge pull request #178247 from mrbullwinkle/mrb_11_1_2021-updates_001

v-andreaco · web-flow · commit f98037daffb7 · 2021-11-02T09:59:57.000-06:00
[Cognitive Services] PM Feedback Q&amp;A
diff --git a/articles/cognitive-services/QnAMaker/includes/new-version.md b/articles/cognitive-services/QnAMaker/includes/new-version.md
@@ -9,4 +9,4 @@ ms.date: 09/15/2021
 ---
 
 > [!NOTE]
-> A newer version of question and answering capability is now available as part of Azure Cognitive Service for Language. For more information see [Azure Cognitive Service for Language Documentation](../../language-service/index.yml). For question answering capabilities within the Language Service, see [question answering](../../language-service/question-answering/overview.md). For information on migrating existing knowledge bases consult the [migration guide](../../language-service/question-answering/how-to/migrate-qnamaker.md).
+> A newer version of the question and answering capability is now available as part of Azure Cognitive Service for Language. For more information see [Azure Cognitive Service for Language Documentation](../../language-service/index.yml). For question answering capabilities within the Language Service, see [question answering](../../language-service/question-answering/overview.md). For information on migrating existing knowledge bases consult the [migration guide](../../language-service/question-answering/how-to/migrate-qnamaker.md).
diff --git a/articles/cognitive-services/language-service/question-answering/concepts/azure-resources.md b/articles/cognitive-services/language-service/question-answering/concepts/azure-resources.md
@@ -62,19 +62,16 @@ Your custom question answering feature deals with two kinds of keys: **authoring
 
 Use these keys when making requests to the service through APIs.
 
-> [!div class="mx-imgBorder"]
-> ![Screenshot of key management managed preview.](../../../qnamaker/media/qnamaker-how-to-key-management/custom-question-answering-key-management.png)
-
 |Name|Location|Purpose|
 |--|--|--|
 |Authoring/Subscription key|[Azure portal](https://azure.microsoft.com/free/cognitive-services/)|These keys are used to access the Language Service APIs). These APIs let you edit the questions and answers in your knowledge base, and publish your knowledge base. These keys are created when you create a new resource.<br><br>Find these keys on the **Cognitive Services** resource on the **Keys and Endpoint** page.|
 |Azure Cognitive Search Admin Key|[Azure portal](../../../../search/search-security-api-keys.md)|These keys are used to communicate with the Azure cognitive search service deployed in the user’s Azure subscription. When you associate an Azure Cognitive Search resource with the custom question answering feature, the admin key is automatically passed to question answering. <br><br>You can find these keys on the **Azure Cognitive Search** resource on the **Keys** page.|
 
 ### Find authoring keys in the Azure portal
 
-You can view and reset your authoring keys from the Azure portal, where you added the Custom question answering (Preview) feature in Text Analytics resource.
+You can view and reset your authoring keys from the Azure portal, where you added the custom question answering feature in your language resource.
 
-1. Go to the Text Analytics resource in the Azure portal and select the resource that has the *Cognitive Services* type:
+1. Go to the language resource in the Azure portal and select the resource that has the *Cognitive Services* type:
 
     > [!div class="mx-imgBorder"]
     > ![Screenshot of question answering resource list.](../../../qnamaker/media/qnamaker-how-to-setup-service/resources-created-question-answering.png)
diff --git a/articles/cognitive-services/language-service/question-answering/concepts/precise-answering.md b/articles/cognitive-services/language-service/question-answering/concepts/precise-answering.md
@@ -33,7 +33,3 @@ The service also returns back the confidence score of the precise answer as an *
 ## Deploying a bot
 
 When you publish a bot, you get the precise answer enabled experience by default in your application, where you will see short answer along with the answer passage. Refer to the API reference for REST API to see how to use the precise answer (called AnswerSpan) in the response. User has the flexibility to choose other experiences by updating the template through the Bot app service.
-
-## Language support
-
-Currently the precise answer feature is only supported for English.
diff --git a/articles/cognitive-services/language-service/question-answering/how-to/chit-chat.md b/articles/cognitive-services/language-service/question-answering/how-to/chit-chat.md
@@ -11,7 +11,7 @@ ms.date: 11/02/2021
 ms.custom: language-service-question-answering, ignite-fall-2021
 ---
 
-# Use chitchat with a knowledge base
+# Use chitchat with a project
 
 Adding chitchat to your bot makes it more conversational and engaging. The chitchat feature in custom question answering allows you to easily add a pre-populated set of the top chitchat, into your knowledge base (KB). This can be a starting point for your bot's personality, and it will save you the time and cost of writing them from scratch.
 
diff --git a/articles/cognitive-services/language-service/question-answering/how-to/create-test-deploy.md b/articles/cognitive-services/language-service/question-answering/how-to/create-test-deploy.md
@@ -8,15 +8,15 @@ ms.date: 11/02/2021
 ms.custom: language-service-question-answering, ignite-fall-2021
 ---
 
-# Create, test, and deploy custom question answering
+# Create, test, and deploy a custom question answering project
 
 You can create a question answering project from your own content, such as FAQs or product manuals. This article includes an example of creating a question answering project from a product manual, to answer questions.
 
 ## Prerequisites
 
 > [!div class="checklist"]
 > * If you don't have an Azure subscription, create a [free account](https://azure.microsoft.com/free/cognitive-services/) before you begin.
-> * A [language resource](https://aka.ms/create-language-resource) with the custom question answering feature enabled. Remember your Azure Active Directory ID, Subscription, language resource name you selected when you created the resource.
+> * A [language resource](https://aka.ms/create-language-resource) with the custom question answering feature enabled.
 
 ## Create your first question answering project
 
@@ -53,7 +53,7 @@ You can create a question answering project from your own content, such as FAQs
     |--------|---------|
     |Surface Book User Guide |https://download.microsoft.com/download/7/B/1/7B10C82E-F520-4080-8516-5CF0D803EEE0/surface-book-user-guide-EN.pdf |
 
-    The extraction process takes a few moments to read the document and identify questions and answers.
+    The extraction process takes a few moments to read the document and identify questions and answers. Question and answering will determine if the underlying content is structured or unstructured.
 
     After successfully adding the source, you can then edit the source contents to add more custom question answer sets.
 
diff --git a/articles/cognitive-services/language-service/question-answering/how-to/network-isolation.md b/articles/cognitive-services/language-service/question-answering/how-to/network-isolation.md
@@ -40,16 +40,16 @@ Private endpoints are provided by [Azure Private Link](../../../../private-link/
 5. Go to *Networking* tab of language resource and under the *Allow access from*, select the *Selected Networks and private endpoints* option and select *save*.
  
 > [!div class="mx-imgBorder"]
-> ![Text Analytics newtorking](../../../QnAMaker/media/qnamaker-reference-private-endpoints/private-endpoint-networking-custom-qna.png)
+> ![Text Analytics networking](../../../QnAMaker/media/qnamaker-reference-private-endpoints/private-endpoint-networking-custom-qna.png)
 
 This will establish a private endpoint connection between language resource and Azure Cognitive Search service instance. You can verify the Private endpoint connection on the *Networking* tab of the Azure Cognitive Search service instance. Once the whole operation is completed, you are good to use your language resource with question answering enabled.
 
 ![Managed Networking Service](../../../QnAMaker/media/qnamaker-reference-private-endpoints/private-endpoint-networking-3.png)
 
 ## Support details
- * We don't support changes to Azure Cognitive Search service once you enable private access to your Text Analytics service. If you change the Azure Cognitive Search service via 'Features' tab after you have enabled private access, the Text Analytics service will become unusable.
+ * We don't support changes to Azure Cognitive Search service once you enable private access to your language resources. If you change the Azure Cognitive Search service via 'Features' tab after you have enabled private access, the language resource will become unusable.
 
- * After establishing Private Endpoint Connection, if you switch Azure Cognitive Search Service Networking to 'Public', you won't be able to use the Text Analytics service. Azure Search Service Networking needs to be 'Private' for the Private Endpoint Connection to work.
+ * After establishing Private Endpoint Connection, if you switch Azure Cognitive Search Service Networking to 'Public', you won't be able to use the language resource. Azure Search Service Networking needs to be 'Private' for the Private Endpoint Connection to work.
 
 ## Restrict access to Cognitive Search resource
 
diff --git a/articles/cognitive-services/language-service/question-answering/language-support.md b/articles/cognitive-services/language-service/question-answering/language-support.md
@@ -13,12 +13,10 @@ ms.custom: language-service-question-answering, ignite-fall-2021
 
 # Language support for custom question answering and knowledge bases
 
-This article describes the language support options for custom question answering enabled resources and knowledge bases. 
+This article describes the language support options for custom question answering enabled resources and knowledge bases.
 
 In custom question answering, you have the option to either select the language each time you add a new project to a resource allowing multiple language support, or you can select a language that will apply to all future projects for a resource.
 
-If you choose to enable the language setting across all your projects you cannot disable this setting.
-
 ## Supporting multiple languages in one custom question answering enabled resource
 
 > [!div class="mx-imgBorder"]
@@ -45,7 +43,7 @@ If you **select the option to set the language used by all projects associated w
 
 ## Languages supported
 
-The following list contains the languages supported for a QnA Maker resource. 
+The following list contains the languages supported for a question answering resource.
 
 | Language |
 |--|
@@ -106,7 +104,7 @@ The following list contains the languages supported for a QnA Maker resource.
 ## Query matching and relevance
 Custom question answering depends on [Azure Cognitive Search language analyzers](/rest/api/searchservice/language-support) for providing results.
 
-While the Azure Cognitive Search capabilities are on par for supported languages, QnA Maker has an additional ranker that sits above the Azure search results. In this ranker model, we use some special semantic and word-based features in the following languages.
+While the Azure Cognitive Search capabilities are on par for supported languages, question answering has an additional ranker that sits above the Azure search results. In this ranker model, we use some special semantic and word-based features in the following languages.
 
 |Languages with additional ranker|
 |--|
diff --git a/articles/cognitive-services/language-service/question-answering/overview.md b/articles/cognitive-services/language-service/question-answering/overview.md
@@ -9,11 +9,11 @@ keywords: "qna maker, low code chat bots, multi-turn conversations"
 ms.custom: language-service-question-answering, ignite-fall-2021
 ---
 
-# What is question answering
+# What is question answering?
 
 Question answering provides cloud-based Natural Language Processing (NLP) that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custom knowledge base (KB) of information.
 
-Question answering is commonly used to build conversational client applications, which include social media applications, chat bots, and speech-enabled desktop applications.
+Question answering is commonly used to build conversational client applications, which include social media applications, chat bots, and speech-enabled desktop applications. Several new features have been added including enhanced relevance using a deep learning ranker, precise answers, and end-to-end region support.
 
 This documentation contains the following article types:
 
@@ -24,14 +24,14 @@ This documentation contains the following article types:
 
 ## When to use question answering
 
-* **When you have static information** - Use question answering when you have static information in your knowledge base of answers. This knowledge base is custom to your needs, which you've built with documents such as [PDFs and URLs](../../qnamaker/Concepts/data-sources-and-content.md).
+* **When you have static information** - Use question answering when you have static information in your knowledge base of answers. This knowledge base is custom to your needs, which you've built with documents such as PDFs and URLs.
 * **When you want to provide the same answer to a request, question, or command** - when different users submit the same question, the same answer is returned.
-* **When you want to filter static information based on meta-information** - add [metadata](../../qnamaker/how-to/metadata-generateanswer-usage.md) tags to provide additional filtering options relevant to your client application's users and the information. Common metadata information includes [chit-chat](./how-to/chit-chat.md), content type or format, content purpose, and content freshness. <!--TODO: Fix Link-->
-* **When you want to manage a bot conversation that includes static information** - your knowledge base takes a user's conversational text or command and answers it. If the answer is part of a pre-determined conversation flow, represented in your knowledge base with [multi-turn context](../../qnamaker/how-to/multiturn-conversation.md), the bot can easily provide this flow.
+* **When you want to filter static information based on meta-information** - add [metadata](./tutorials/multiple-domains.md) tags to provide additional filtering options relevant to your client application's users and the information. Common metadata information includes [chit-chat](./how-to/chit-chat.md), content type or format, content purpose, and content freshness. <!--TODO: Fix Link-->
+* **When you want to manage a bot conversation that includes static information** - your knowledge base takes a user's conversational text or command and answers it. If the answer is part of a pre-determined conversation flow, represented in your knowledge base with [multi-turn context](./tutorials/guided-conversations.md), the bot can easily provide this flow.
 
 ## What is a knowledge base?
 
-Question answering [imports your content](../../qnamaker/Concepts/plan.md) into a knowledge base of question and answer pairs. The import process extracts information about the relationship between the parts of your structured and semi-structured content to imply relationships between the question and answer pairs. You can edit these question and answer pairs or add new pairs.
+Question answering [imports your content](./how-to/manage-knowledge-base.md) into a knowledge base of question and answer pairs. The import process extracts information about the relationship between the parts of your structured and semi-structured content to imply relationships between the question and answer pairs. You can edit these question and answer pairs or add new pairs.
 
 The content of the question and answer pair includes:
 * All the alternate forms of the question
diff --git a/articles/cognitive-services/language-service/question-answering/tutorials/adding-synonyms.md b/articles/cognitive-services/language-service/question-answering/tutorials/adding-synonyms.md
@@ -75,8 +75,7 @@ As you can see, when `troubleshoot` was not added as a synonym, we got a low con
 
 > [!NOTE]
 > Synonyms are case insensitive. Synonyms also might not work as expected if you add stop words as synonyms. The list of stop words can be found here: [List of stop words](https://github.com/Azure-Samples/azure-search-sample-data/blob/master/STOPWORDS.md).
-
-For instance, if you add the abbreviation **IT** for Information technology, the system might not be able to recognize Information Technology because **IT** is a stop word and is filtered when a query is processed.
+> For instance, if you add the abbreviation **IT** for Information technology, the system might not be able to recognize Information Technology because **IT** is a stop word and is filtered when a query is processed.
 
 ## Next steps
 
diff --git a/articles/cognitive-services/language-service/question-answering/tutorials/bot-service.md b/articles/cognitive-services/language-service/question-answering/tutorials/bot-service.md
@@ -10,7 +10,7 @@ ms.custom: language-service-question-answering, ignite-fall-2021
 
 # Tutorial: Create a FAQ bot
 
-Create a FAQ Bot with question answering and Azure [Bot Service](https://azure.microsoft.com/services/bot-service/) with no code.
+Create a FAQ Bot with custom question answering and Azure [Bot Service](https://azure.microsoft.com/services/bot-service/) with no code.
 
 In this tutorial, you learn how to:
 
diff --git a/articles/cognitive-services/language-service/question-answering/tutorials/multiple-domains.md b/articles/cognitive-services/language-service/question-answering/tutorials/multiple-domains.md
@@ -1,6 +1,6 @@
 ---
-title: "Tutorial: Create a FAQ bot for multiple domains with Azure Bot Service"
-description: In this tutorial, create a no code FAQ Bot for production use cases with QnA Maker and Azure Bot Service.
+title: "Tutorial: Create a FAQ bot for multiple categories with Azure Bot Service"
+description: In this tutorial, create a no code FAQ Bot for production use cases with question answering and Azure Bot Service.
 ms.service: cognitive-services
 ms.subservice: language-service
 ms.topic: tutorial
@@ -10,12 +10,12 @@ ms.date: 11/02/2021
 ms.custom: language-service-question-answering, ignite-fall-2021
 ---
 
-# Add multiple domains to your FAQ bot
+# Add multiple categories to your FAQ bot
 
 In this tutorial, you learn how to:
 
 > [!div class="checklist"]
-> * Create a project and tag question answer pairs into distinct domains with metadata
+> * Create a project and tag question answer pairs into distinct categories with metadata
 > * Create a separate project for each domain
 > * Create a separate language resource for each domain
 
@@ -100,4 +100,4 @@ When the user question is received by the service, you would need to pass on the
 
 ## Create a separate language resource for each domain
 
-Let's say the marketing team at Microsoft wants to build a customer support bot that answers user queries on Surface and Xbox products. They plan to assign distinct teams to access knowledge bases on Surface and Xbox. In this case, it is advised to create two QnA Maker resources - one for Surface and another for Xbox. You can however define distinct roles for users accessing the same resource.
+Let's say the marketing team at Microsoft wants to build a customer support bot that answers user queries on Surface and Xbox products. They plan to assign distinct teams to access knowledge bases on Surface and Xbox. In this case, it is advised to create two question answering resources - one for Surface and another for Xbox. You can however define distinct roles for users accessing the same resource.
diff --git a/articles/cognitive-services/language-service/question-answering/tutorials/multiple-languages.md b/articles/cognitive-services/language-service/question-answering/tutorials/multiple-languages.md
@@ -16,7 +16,6 @@ In this tutorial, you learn how to:
 
 <!-- green checkmark -->
 > [!div class="checklist"]
-> * Create a project that supports multiple languages
 > * Create a project that supports English
 > * Create a project that supports German
 
@@ -29,7 +28,7 @@ To be able to create a project in more than one language, the multiple language
 > [!div class="mx-imgBorder"]
 > [ ![Screenshot of UI for create project with I want to select the language when I create a project in this resource selected.]( ../media/multiple-languages/multiple-languages.png) ](../media/multiple-languages/multiple-languages.png#lightbox)
 
-1. From the [Language Studio](https://aka.ms/languageStudio), open the question answering page. Select **Create new project** > **I want to select the language when I create a project in this resource** > **Next**.
+1. From the [Language Studio](https://aka.ms/languageStudio) home page, select open custom question answering. Select **Create new project** > **I want to select the language when I create a project in this resource** > **Next**.
 
 2. Fill out enter basic information page and select **Next** > **Create project**.
 
