@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: best-practice
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.author: lajanuar
 ms.custom: language-service-clu
 ---
@@ -112,7 +112,7 @@ If you enable this feature, the utterance count of your training set increases.
 
 ## Address model overconfidence
 
-Customers can use the LoraNorm traning configuration version if the model is being incorrectly overconfident. An example of this behavior can be like the following scenario where the model predicts the incorrect intent with 100% confidence. This score makes the confidence threshold project setting unusable.
+Customers can use the LoraNorm training configuration version if the model is being incorrectly overconfident. An example of this behavior can be like the following scenario where the model predicts the incorrect intent with 100% confidence. This score makes the confidence threshold project setting unusable.
 
 | Text |	Predicted intent |	Confidence score |
 |----|----|----|
@@ -272,6 +272,6 @@ After the request is sent, you can track the progress of the training job in Lan
 
 Caveats:
 
-- The None score threshold for the app (confidence threshold below which `topIntent` is marked as `None`) when you use this training configuration should be set to 0. This setting is used because this new training configuration attributes a certain portion of the in-domain probabilities to out of domain so that the model isn't incorrectly overconfident about in-domain utterances. As a result, users might see slightly reduced confidence scores for in-domain utterances as compared to the prod training configuration.
+- The None score threshold for the app (confidence threshold below which `topIntent` is marked as `None`) when you use this training configuration should be set to 0. This setting is used because this new training configuration attributes a certain portion of the in-domain probabilities to out of domain so that the model isn't incorrectly overconfident about in-domain utterances. As a result, users might see slightly reduced confidence scores for in-domain utterances as compared to the production training configuration.
 - We don't recommend this training configuration for apps with only two intents, such as `IntentA` and `None`, for example.
 - We don't recommend this training configuration for apps with a low number of utterances per intent. We highly recommend a minimum of 25 utterances per intent.

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.author: lajanuar
 ms.custom: language-service-clu
 ---

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.author: lajanuar
 ms.custom: language-service-clu
 ---

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: faq
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.author: lajanuar
 ms.custom: mode-other
 ---

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.author: lajanuar
 ms.custom: language-service-clu
 ---
@@ -18,7 +18,7 @@ You can query the deployment programmatically through the [prediction API](https
 
 ## Test deployed model
 
-You can use Language Studio to submit an utterance, get predictions and visualize the results.
+You can use Language Studio to submit an utterance, get predictions, and visualize the results.
 
 [!INCLUDE [Test model](../includes/language-studio/test-model.md)]
 
@@ -32,7 +32,7 @@ You can use Language Studio to submit an utterance, get predictions and visualiz
 
 # [REST APIs](#tab/REST-APIs)
 
-First you will need to get your resource key and endpoint:
+First you'll need to get your resource key and endpoint:
 
 [!INCLUDE [Get keys and endpoint Azure Portal](../includes/get-keys-endpoint-azure.md)]
 
@@ -53,7 +53,7 @@ You can also use the client libraries provided by the Azure SDK to send requests
 
 1. Go to your resource overview page in the [Azure portal](https://portal.azure.com/#home)
 
-2. From the menu on the left side, select **Keys and Endpoint**. Use endpoint for the API requests and you will need the key for `Ocp-Apim-Subscription-Key` header.
+2. From the menu on the left side, select **Keys and Endpoint**. Use endpoint for the API requests and you'll need the key for `Ocp-Apim-Subscription-Key` header.
 
     :::image type="content" source="../../custom-text-classification/media/get-endpoint-azure.png" alt-text="A screenshot showing a key and endpoint in the Azure portal." lightbox="../../custom-text-classification/media/get-endpoint-azure.png":::
 

@@ -11,7 +11,7 @@ ms.author: lajanuar
 ms.custom: language-service-clu
 ---
 
-# Language support for conversational language understanding
+# Language support for Conversational Language Understanding (CLU)
 
 Use this article to learn about the languages currently supported by CLU feature.
 

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.author: lajanuar
 ms.custom: language-service-clu
 ---

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.author: lajanuar
 ms.custom: language-service-clu, references_regions
 ---

@@ -5,10 +5,9 @@ keywords: conversational language understanding, bot framework, bot, language un
 author: laujan
 ms.author: lajanuar
 manager: nitinme
-ms.reviewer: cahann, hazemelh
 ms.service: azure-ai-language
 ms.topic: tutorial
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ---
 
 # Integrate conversational language understanding with Bot Framework

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: how-to
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.author: lajanuar
 ms.custom: language-service-language-detection
 ---
@@ -49,7 +49,7 @@ Analysis is performed upon receipt of the request. Using the language detection
 
 When you get results from language detection, you can stream the results to an application or save the output to a file on the local system.
 
-Language detection will return one predominant language for each document you submit, along with it's [ISO 639-1](https://www.iso.org/standard/22109.html) name, a human-readable name, a confidence score, script name and script code according to the [ISO 15924 standard](https://wikipedia.org/wiki/ISO_15924). A positive score of 1 indicates the highest possible confidence level of the analysis.
+Language detection will return one predominant language for each document you submit, along with it's [ISO 639-1](https://www.iso.org/standard/22109.html) name, a human-readable name, a confidence score, script name, and script code according to the [ISO 15924 standard](https://wikipedia.org/wiki/ISO_15924). A positive score of 1 indicates the highest possible confidence level of the analysis.
 
 
 ### Ambiguous content

@@ -6,14 +6,14 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.author: lajanuar
 ms.custom: language-service-pii, build-2024
 ---
 
 # Personally Identifiable Information (PII) detection language support 
 
-Use this article to learn which natural languages are supported by the text PII, document PII, and conversation PII features of Azure AI Language.
+Use this article to learn which natural languages are supported by the text PII, document PII, and conversation PII features of Azure AI Language Service.
 # [Text PII](#tab/text)
 
 ## Text PII language support

@@ -1,20 +1,20 @@
 ---
-title: Confidence score - custom question answering
+title: Confidence score - Custom question answering
 titleSuffix: Azure AI services
-description: When a user query is matched against a knowledge base, custom question answering returns relevant answers, along with a confidence score.
+description: When a user query is matched against a knowledge base, Custom question answering returns relevant answers, along with a confidence score.
 #services: cognitive-services
 manager: nitinme
 author: laujan
 ms.author: lajanuar
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.custom: language-service-question-answering
 ---
 
 # Confidence score
 
-When a user query is matched against a project (also known as a knowledge base), custom question answering returns relevant answers, along with a confidence score. This score indicates the confidence that the answer is the right match for the given user query.
+When a user query is matched against a project (also known as a knowledge base), Custom question answering returns relevant answers, along with a confidence score. This score indicates the confidence that the answer is the right match for the given user query.
 
 The confidence score is a number between 0 and 100. A score of 100 is likely an exact match, while a score of 0 means, that no matching answer was found. The higher the score- the greater the confidence in the answer. For a given query, there could be multiple answers returned. In that case, the answers are returned in order of decreasing confidence score.
 
@@ -31,7 +31,7 @@ The following table indicates typical confidence associated for a given score.
 
 ## Choose a score threshold
 
-The table above shows the range of scores that can occur when querying with custom question answering. However, since every project is different, and has different types of words, intents, and goals- we recommend you test and choose the threshold that best works for you. By default the threshold is set to `0`, so that all possible answers are returned. The recommended threshold that should work for most projects, is **50**.
+The table above shows the range of scores that can occur when querying with Custom question answering. However, since every project is different, and has different types of words, intents, and goals- we recommend you test and choose the threshold that best works for you. By default the threshold is set to `0`, so that all possible answers are returned. The recommended threshold that should work for most projects, is **50**.
 
 When choosing your threshold, keep in mind the balance between **Accuracy** and **Coverage**, and adjust your threshold based on your requirements.
 

@@ -6,10 +6,10 @@ ms.author: lajanuar
 author: laujan
 ms.manager: nitinme
 ms.topic: how-to
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.custom: language-service-question-answering
 ---
-# Migrate from QnA Maker to custom question answering 
+# Migrate from QnA Maker to Custom question answering 
 
 **Purpose of this document:** This article aims to provide information that can be used to successfully migrate applications that use QnA Maker to custom question answering. Using this article, we hope customers gain clarity on the following: 
 
@@ -23,7 +23,7 @@ ms.custom: language-service-question-answering
 **Intended Audience:** Existing QnA Maker customers
 
 > [!IMPORTANT]
-> Custom question Answering, a feature of Azure AI Language was introduced in November 2021 with several new capabilities including enhanced relevance using a deep learning ranker, precise answers, and end-to-end region support. Each custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) aren't migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration:
+> Custom question Answering, a feature of Azure AI Language was introduced in November 2021 with several new capabilities including enhanced relevance using a deep learning ranker, precise answers, and end-to-end region support. Each Custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) aren't migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration:
 >
 >  - Automatic RBAC to Language project (not resource)
 >  - Automatic enabling of analytics.
@@ -113,7 +113,7 @@ This topic compares two hypothetical scenarios when migrating from QnA Maker to
 > An attempt has been made to ensure these scenarios are representative of real customer migrations, however, individual customer scenarios differ. Also, this article doesn't include pricing details. Visit the [pricing](https://azure.microsoft.com/pricing/details/cognitive-services/language-service/) page for more information.
 
 > [!IMPORTANT] 
-> Each custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) aren't migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration. You'll also need to [re-enable analytics](analytics.md) for the language resource.
+> Each Custom question answering project is equivalent to a knowledge base in QnA Maker. Resource level settings such as Role-based access control (RBAC) aren't migrated to the new resource. These resource level settings would have to be reconfigured for the language resource post migration. You'll also need to [re-enable analytics](analytics.md) for the language resource.
 
 ### Migration scenario 1: No custom authoring portal
 

@@ -5,13 +5,13 @@ ms.service: azure-ai-language
 ms.topic: how-to
 ms.author: lajanuar
 author: laujan
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.custom: language-service-question-answering
 ---
 
 # Migrate from QnA Maker knowledge bases to custom question answering
 
-Custom question answering, a feature of Azure AI Language was introduced in May 2021 with several new capabilities including enhanced relevance using a deep learning ranker, precise answers, and end-to-end region support. Each custom question answering project is equivalent to a knowledge base in QnA Maker. You can easily migrate knowledge bases from a QnA Maker resource to custom question answering projects within a [language resource](https://aka.ms/create-language-resource). You can also choose to migrate knowledge bases from multiple QnA Maker resources to a specific language resource.
+Custom question answering, a feature of Azure AI Language was introduced in May 2021 with several new capabilities including enhanced relevance using a deep learning ranker, precise answers, and end-to-end region support. Each Custom question answering project is equivalent to a knowledge base in QnA Maker. You can easily migrate knowledge bases from a QnA Maker resource to custom question answering projects within a [language resource](https://aka.ms/create-language-resource). You can also choose to migrate knowledge bases from multiple QnA Maker resources to a specific language resource.
 
 To successfully migrate knowledge bases, **the account performing the migration needs contributor access to the selected QnA Maker and language resource**. When a knowledge base is migrated, the following details are copied to the new custom question answering project:
 

@@ -1,11 +1,11 @@
 ---
 title: Enrich your project with active learning
-description: In this tutorial, learn how to enrich your custom question answering projects with active learning
+description: In this tutorial, learn how to enrich your Custom question answering projects with active learning
 ms.service: azure-ai-language
 ms.topic: tutorial
 author: laujan
 ms.author: lajanuar
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.custom: language-service-question-answering
 ---
 
@@ -20,13 +20,13 @@ In this tutorial, you learn how to:
 > * Accept/reject active learning suggestions
 > * Add alternate questions
 
-This tutorial shows you how to enhance your custom question answering project with active learning. If you notice that customers are asking questions that are not covered in your project, they may be paraphrased variations of questions.
+This tutorial shows you how to enhance your Custom question answering project with active learning. If you notice that customers are asking questions that are not covered in your project, they may be paraphrased variations of questions.
 
 These variations, when added as alternate questions to the relevant question answer pair, help to optimize the project to answer real world user queries. You can manually add alternate questions to question answer pairs through the editor. At the same time, you can also use the active learning feature to generate active learning suggestions based on user queries. The active learning feature, however, requires that the project receives regular user traffic to generate suggestions.
 
 ## Use active learning
 
-Active learning is turned on by default for custom question answering enabled resources.
+Active learning is turned on by default for Custom question answering enabled resources.
 
 To try out active learning suggestions, you can import the following file as a new project: [SampleActiveLearning.tsv](https://github.com/Azure-Samples/cognitive-services-sample-data-files/blob/master/qna-maker/knowledge-bases/SampleActiveLearning.tsv).
 

@@ -5,7 +5,7 @@ ms.service: azure-ai-language
 ms.topic: tutorial
 author: laujan
 ms.author: lajanuar
-ms.date: 11/21/2024
+ms.date: 06/04/2025
 ms.custom: language-service-question-answering
 ---
 
@@ -63,7 +63,7 @@ Using the editor, we add a new QnA pair with a follow-up prompt by clicking on *
     > [!div class="mx-imgBorder"]
     > [ ![Screenshot of UI with "add a follow-up prompt" highlighted in a red box]( ../media/guided-conversations/add-prompts.png) ]( ../media/guided-conversations/add-prompts.png#lightbox)
     
-    We provide **Check Compatibility** as the “Display text” for the prompt and try to link it to a QnA. Since, no related QnA pair is available to link to the prompt, when we search “Check your Surface Pen Compatibility”, we create a new question pair by clicking on **Create link to new pair** and select **Done**. Then select **Save changes**.
+    We provide **Check Compatibility** as the "Display text" for the prompt and try to link it to a QnA. Since, no related QnA pair is available to link to the prompt, when we search “Check your Surface Pen Compatibility”, we create a new question pair by clicking on **Create link to new pair** and select **Done**. Then select **Save changes**.
     
     > [!div class="mx-imgBorder"]
     > [ ![Screenshot of a question and answer about checking your surface pen compatibility]( ../media/guided-conversations/compatability-check.png) ]( ../media/guided-conversations/compatability-check.png#lightbox)

@@ -16,6 +16,14 @@ Azure AI Language is updated on an ongoing basis. Bookmark this page to stay up
 
 ## May 2025
 
+##### 2025-05-15-preview release
+
+The [latest API preview version](/rest/api/language/operation-groups?view=rest-language-2025-05-15-preview&preserve-view=true) includes updates for named entity recognition (NER) and PII detection:
+
+* New entity type support for `DateOfBirth`, `BankAccountNumber`, `PassportNumber`, and `DriversLicenseNumber`.
+
+* Improved AI quality for `PhoneNumber` entity type.
+
 ##### New agent templates 
 
 Azure AI Language now supports the following agent templates:
@@ -34,16 +42,19 @@ Azure AI Language introduces new customization and entity subtype features for P
 
 *  [Use entity synonyms for tailored PII detection](personally-identifiable-information/how-to/adapt-to-domain-pii.md#api-schema-for-the-entitysynoyms-parameter).
 
-##### 2025-05-15-preview release. 
+##### Enhanced CLU and CQA Capabilities in Azure AI Foundry
 
-The [latest API preview version](/rest/api/language/operation-groups?view=rest-language-2025-05-15-preview&preserve-view=true) includes updates for named entity recognition (NER) and PII detection:
+Azure AI Foundry now offers enhanced capabilities for fine-tuning with custom conversational language understanding (CLU) and conversational question-and-answer (CQA) AI features:
 
-* New entity type support for `DateOfBirth`, `BankAccountNumber`, `PassportNumber`, and `DriversLicenseNumber`.
+*	CLU and CQA authoring tools are now available in Azure AI Foundry.
+  
+*	CLU offers a quick deploy option powered by large language models (LLMs) for rapid deployment.
 
-* Improved AI quality for `PhoneNumber` entity type.
+*	CQA incorporates the QnA Maker scoring algorithm for more accurate responses.
 
-To learn more, see our latest [TechCommunity Blog Post](https://techcommunity.microsoft.com/blog/azure-ai-services-blog/announcing-azure-ai-language-new-features-to-accelerate-your-agent-development/4415216).
+*	CQA enables exact match answering for precise query resolutions.
 
+###### For more updates, see our latest [TechCommunity Blog Post](https://techcommunity.microsoft.com/blog/azure-ai-services-blog/announcing-azure-ai-language-new-features-to-accelerate-your-agent-development/4415216).
 
 ## April 2025