July freshness

laujan · laujan · commit 502277fa576d · 2025-07-22T14:17:59.000-07:00
diff --git a/articles/ai-services/language-service/concepts/model-lifecycle.md b/articles/ai-services/language-service/concepts/model-lifecycle.md
@@ -6,34 +6,34 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: conceptual
-ms.date: 01/31/2025
+ms.date: 07/22/2025
 ms.author: lajanuar
 ---
 
 # Model lifecycle
 
-Language service features utilize AI models. We update the language service with new model versions to improve accuracy, support, and quality. As models become older, they are retired. Use this article for information on that process, and what you can expect for your applications.
+Language service features utilize AI models. We update the language service with new model versions to improve accuracy, support, and quality. As models become older, they're retired. Use this article for information on that process, and what you can expect for your applications.
 
 ## Prebuilt features
 
-Our standard (not customized) language service features are built on AI models that we call pre-trained or prebuilt models.
+Our standard (not customized) language service features are built on AI models that we call pretrained or prebuilt models.
 
 We regularly update the language service with new model versions to improve model accuracy, support, and quality.
 
-By default, all API requests will use the latest Generally Available (GA) model.
+By default, all API requests use the latest Generally Available (GA) model.
 
 #### Choose the model-version used on your data
 
-We recommend using the `latest` model version to utilize the latest and highest quality models. As our models improve, it’s possible that some of your model results may change. Model versions may be deprecated, so we no longer accept specified GA model versions in your implementation. 
+We recommend using the `latest` model version to utilize the latest and highest quality models. As our models improve, it's possible that some of your model results may change. Model versions may be deprecated, so we no longer accept specified GA model versions in your implementation. 
 
-Preview models used for preview features do not maintain a minimum retirement period and may be deprecated at any time.
+Preview models used for preview features don't maintain a minimum retirement period and may be deprecated at any time.
 
-By default, API and SDK requests will use the latest Generally Available model. To use a model in preview, you can use an optional parameter `modelVersion` to select the preview version of the model to be used (not recommended for GA models).
+By default, API and SDK requests use the latest Generally Available model. To use a model in preview, you can use an optional parameter `modelVersion` to select the preview version of the model to be used (not recommended for GA models).
 
 > [!NOTE]
-> If you are using a model version that is not listed in the table, then it was subjected to the expiration policy.
+> If you're using a model version that isn't listed in the table, then it was subjected to the expiration policy.
 
-Use the table below to find which model versions are supported by each feature:
+Use the following table to find which model versions support each feature:
 
 | Feature                                             | Supported generally available (GA) version     | Latest supported preview versions           |
 |-----------------------------------------------------|------------------------------------------------|---------------------------------------------|
@@ -55,7 +55,7 @@ Use the table below to find which model versions are supported by each feature:
 
 For custom features, there are two key parts of the AI implementation: training and deployment. New configurations are released regularly with regular AI improvements, so older and less accurate configurations are retired. 
 
-Use the table below to find which model versions are supported by each feature:
+Use the following table to find which model versions support each feature:
 
 | Feature                                     | Supported Training Config Versions         | Training Config Expiration         | Deployment Expiration  |
 |---------------------------------------------|--------------------------------------------|------------------------------------|------------------------|
@@ -66,24 +66,23 @@ Use the table below to find which model versions are supported by each feature:
 
 ** *For latest training configuration versions, the posted expiration dates are subject to availability of a newer model version. If no newer model versions are available, the expiration date may be extended.*
 
-Training configurations are typically available for **six months** after its release. If you've assigned a trained configuration to a deployment, this deployment expires after **twelve months** from the training config expiration. If your models are about to expire, you can retrain and redeploy your models with the latest training configuration version. 
+Training configurations are typically available for **six months** after its release. If you assigned a trained configuration to a deployment, this deployment expires after **twelve months** from the training config expiration. If your models are about to expire, you can retrain and redeploy your models with the latest training configuration version. 
 
 > [!TIP]
-> It's recommended to use the latest supported configuration version.
+> We recommend that you use the latest supported configuration version.
 
 After the **training config expiration** date, you'll have to use another supported training configuration version to submit any training or deployment jobs. After the **deployment expiration** date, your deployed model will be unavailable to be used for prediction.
 
 After training config version expires, API calls will return an error when called or used if called with an expired configuration version. By default, training requests use the latest available training configuration version. To change the configuration version, use the `trainingConfigVersion` parameter when submitting a training job and assign the version you want.
 
 
-
 ## API versions
 
-When you're making API calls to the following features, you need to specify the `API-VERISON` you want to use to complete your request. It's recommended to use the latest available API versions.
+When you're making API calls to the following features, you need to specify the `API-VERISON` you want to use to complete your request. We recommend that you use the latest available API version.
 
-If you're using [Language Studio](https://aka.ms/languageStudio) for your projects, you'll use the latest API version available. Other API versions are only available through the REST APIs and client libraries.
+If you're using [Language Studio](https://aka.ms/languageStudio) for your projects, you use the latest API version available. Other API versions are only available through the REST APIs and client libraries.
 
-Use the following table to find which API versions are supported by each feature:
+Use the following table to find which API versions support each feature:
 
 |Feature                               |Supported versions                                                                   |Latest Generally Available version                           |Latest preview version|
 |--------------------------------------|-------------------------------------------------------------------------------------|----------------------------------|----------------------|
diff --git a/articles/ai-services/language-service/custom-named-entity-recognition/quickstart.md b/articles/ai-services/language-service/custom-named-entity-recognition/quickstart.md
@@ -6,20 +6,21 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: quickstart
-ms.date: 01/31/2025
+ms.date: 07/22/2025
 ms.author: lajanuar
 ms.custom: language-service-custom-ner, mode-other
 zone_pivot_groups: usage-custom-language-features
 ---
 
 # Quickstart: Custom named entity recognition
 
-Use this article to get started with creating a custom NER project where you can train custom models for custom entity recognition. A model is artificial intelligence software that's trained to do a certain task. For this system, the models extract named entities and are trained by learning from tagged data.
+Use this article to get started with creating a custom NER project where you can train custom models for custom entity recognition. A model artificial intelligence software trained to achieve a specific task. For this system, the models extract named entities and are trained by learning from tagged data.
+
+In this article, we use Language Studio to demonstrate key concepts of custom Named Entity Recognition (NER). As an example, let's build a custom NER model to extract the following relevant entities from loan agreements:
 
-In this article, we use Language Studio to demonstrate key concepts of custom Named Entity Recognition (NER). As an example we’ll build a custom NER model to extract relevant entities from loan agreements, such as the:
 * Date of the agreement
-* Borrower's name, address, city and state  
-* Lender's name, address, city and state  
+* Borrower's name, address, city, and state
+* Lender's name, address, city, and state
 * Loan and interest amounts
 
 ::: zone pivot="language-studio"
@@ -36,11 +37,9 @@ In this article, we use Language Studio to demonstrate key concepts of custom Na
 
 ## Next steps
 
-After you've created entity extraction model, you can:
-
-* [Use the runtime API to extract entities](how-to/call-api.md)
+After you create your entity extraction model, you can [use the runtime API to extract entities](how-to/call-api.md).
 
-When you start to create your own custom NER projects, use the how-to articles to learn more about tagging, training and consuming your model in greater detail:
+As you create your own custom NER projects, use our how-to articles to learn more about tagging, training, and consuming your model in greater detail:
 
 * [Data selection and schema design](how-to/design-schema.md)
 * [Tag data](how-to/tag-data.md)
diff --git a/articles/ai-services/translator/containers/configuration.md b/articles/ai-services/translator/containers/configuration.md
@@ -6,16 +6,16 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-translator
 ms.topic: how-to
-ms.date: 01/28/2025
+ms.date: 07/22/2025
 ms.author: lajanuar
 recommendations: false
 ---
 
 # Configure Azure AI Translator Docker containers
 
-Azure AI services provide each container with a common configuration framework. You can easily configure your Translator containers to build Translator application architecture optimized for robust cloud capabilities and edge locality.
+Azure AI services offer a unified configuration framework for all containers. You can easily configure your Translator containers to create a Translator application architecture that is optimized for both robust cloud features and edge locality deployment.
 
-The **Azure AI Translator** container runtime environment is configured using the `docker run` command arguments. This container has both required and optional settings. The required container-specific settings are the billing settings.
+The **Azure AI Translator** container runtime environment is configured using the `docker run` command arguments. This container includes both required and optional settings. The required settings specific to the container are the billing settings.
 
 ## Configuration settings
 
diff --git a/articles/ai-services/translator/containers/deploy-user-managed-glossary.md b/articles/ai-services/translator/containers/deploy-user-managed-glossary.md
@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-translator
 ms.topic: how-to
-ms.date: 01/28/2025
+ms.date: 07/22/2025
 ms.author: lajanuar
 recommendations: false
 ---
@@ -16,9 +16,9 @@ recommendations: false
 
 # Deploy a user-managed glossary
 
-Azure AI Translator containers enable you to run several features of the Translator service in your own environment and are great for specific security and data governance requirements.
+Azure AI Translator containers allow you to use many of the Translator service's features within your own environment, making them ideal for meeting specific security and data governance needs.
 
-There can be times when you're running a container with a multi-layered ingestion process when you discover that you need to implement an update to sentence and/or phrase files. Since the standard phrase and sentence files are encrypted and read directly into memory at runtime, you need to implement a quick-fix engineering solution to implement a dynamic update. This update can be implemented using our user-managed glossary feature:
+Sometimes, when operating a container with a complex ingestion process, you may encounter the need to update sentence or phrase files. Because the default sentence and phrase files are encrypted and loaded directly into memory at runtime, you need a rapid engineering solution to allow for dynamic updates. You can address this need by implementing our user-managed glossary feature:
 
 * To deploy the **phrase&#8203;fix** solution, you need to create a **phrase&#8203;fix** glossary file to specify that a listed phrase is translated in a specified way.
 
diff --git a/articles/ai-services/translator/containers/faq.yml b/articles/ai-services/translator/containers/faq.yml
@@ -6,11 +6,11 @@ metadata:
    manager: nitinme
    ms.service: azure-ai-translator
    ms.topic: faq
-   ms.date: 01/28/2025
+   ms.date: 07/22/2025
    ms.author: lajanuar
 title: Azure AI Translator container FAQ
 summary:  |
-  Find answers to commonly asked questions about concepts related to Azure AI Translator containers.
+  Discover answers to frequently asked questions regarding key concepts associated with Azure AI Translator containers.
 
 sections:
   - name: General questions and concepts
diff --git a/articles/ai-services/translator/containers/overview.md b/articles/ai-services/translator/containers/overview.md
@@ -6,13 +6,13 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-translator
 ms.topic: overview
-ms.date: 01/29/2025
+ms.date: 07/22/2025
 ms.author: lajanuar
 ---
 
 # What are Azure AI Translator containers?
 
-Azure AI Translator containers enable you to build translator application architecture that is optimized for both robust cloud capabilities and edge locality. A container is a running instance of an executable software image. A Translator container image includes all libraries, tools, and dependencies needed to run an application consistently in any private, public, or personal computing environment. Containers are isolated, lightweight, portable, and are great for implementing specific security or data governance requirements. Azure AI Translator containers are available in [connected](#connected-azure-ai-translator-containers) and [disconnected (offline)](#disconnected-azure-ai-translator-containers) modalities.
+Azure AI Translator containers enable you to build translator application architecture that is optimized for both robust cloud capabilities and edge locality. A container is an active running instance of an executable software image that contains everything needed—such as all libraries, tools, and dependencies—to run your application consistently and reliably in any environment, whether it's private, public, or personal. Containers are isolated, lightweight, portable, making them ideal for meeting specific security or data governance requirements. Azure AI Translator containers are available in [connected](#connected-azure-ai-translator-containers) and [disconnected (offline)](#disconnected-azure-ai-translator-containers) modes.
 
 ## Connected Azure AI Translator containers
 
@@ -40,7 +40,7 @@ You're billed for connected containers monthly, based on the usage and consumpti
 
 Disconnected containers are offered through commitment tier pricing offered at a discounted rate compared to Standard pricing. With commitment tier pricing, you can commit to using Translator Service features for a fixed fee, at a predictable total cost, based on the needs of your workload. Commitment plans for disconnected containers have a calendar year commitment period.
 
-When you purchase a plan, you're charged the full price immediately. During the commitment period, you can't change your commitment plan; however you can purchase more units at a pro-rated price for the remaining days in the year. You have until midnight (UTC) on the last day of your commitment, to end a commitment plan.
+When you purchase a plan, you're charged for the full price immediately. During the commitment period, you can't change your commitment plan; however you can purchase more units at a pro-rated price for the remaining days in the year. You have until midnight (UTC) on the last day of your commitment, to end a commitment plan.
 
   ***Sample billing metadata for Translator disconnected container***
 
diff --git a/articles/ai-services/translator/how-to/use-firewalls.md b/articles/ai-services/translator/how-to/use-firewalls.md
@@ -6,15 +6,15 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-translator
 ms.topic: how-to
-ms.date: 01/28/2025
+ms.date: 07/22/2025
 ms.author: lajanuar
 ---
 
 # Use Azure AI Translator behind firewalls
 
-Azure AI Translator can translate behind firewalls using either [Domain-name](/azure/firewall/dns-settings#dns-proxy-configuration) or [IP filtering](#configure-firewall). Domain-name filtering is the preferred method.
+Azure AI Translator can translate behind firewalls by using either [domain-name](/azure/firewall/dns-settings#dns-proxy-configuration) or [IP filtering](#configure-firewall). Domain-name filtering is the recommended approach.
 
-If you still require IP filtering, you can get the [IP addresses details using service tag](/azure/virtual-network/service-tags-overview#discover-service-tags-by-using-downloadable-json-files). Translator is under the **CognitiveServicesManagement** service tag.
+If you still require IP filtering, you can obtain the [IP addresses details using service tag](/azure/virtual-network/service-tags-overview#discover-service-tags-by-using-downloadable-json-files). Translator is included under the **CognitiveServicesManagement** service tag.
 
 ## Configure firewall
 
diff --git a/articles/ai-services/translator/solutions/translator-pro/overview.md b/articles/ai-services/translator/solutions/translator-pro/overview.md
@@ -6,15 +6,15 @@ ms.author: lajanuar
 manager: nitinme
 ms.service: azure-ai-translator
 ms.topic: overview
-ms.date: 01/22/2025
-ms.custom: FY25Q1-Linter, ignite-2024
+ms.date: 07/22/2025
+ms.custom: FY25Q1-Linter
 ---
 
 # What is Microsoft Translator Pro?
 
-Microsoft Translator Pro is an advanced mobile application that enables seamless speech-to-speech translation in real time. Translator Pro is designed specifically for enterprises seeking to eliminate language barriers within the workplace by delivering a standalone, native experience within the enterprise ecosystem.
+Microsoft Translator Pro is an advanced mobile application that enables real-time, seamless speech-to-speech translation. The app is designed specifically for enterprises seeking to eliminate language barriers within the workplace. Translator Pro delivers a dedicated and native experience that fully integrates into the enterprise ecosystem.
 
-Microsoft Translator Pro is a paid mobile application available on the Azure public and US government cloud platform. To utilize the application, enterprise users must authenticate their identities and set up translator resources within the Azure public or US Government cloud environment.
+Microsoft Translator Pro is a paid mobile application available on both the Azure public and US government cloud platforms. To utilize the application, enterprise users must authenticate their identities and configure translator resources within the Azure public or US Government cloud environment.
 
   > [!IMPORTANT]
   >
