resolve build errors

Author: laujan

articles/ai-services/translator/custom-translator/azure-ai-foundry/concepts/dictionaries.md

@@ -14,7 +14,7 @@ ms.custom: cogserv-non-critical-translator
 
 # Dictionary
 
-An Custom translation dictionary is an aligned pair of documents that specifies a list of phrases or sentences and their corresponding translations. Use a dictionary in your training, when you want Custom Translator to translate any instances of the source phrase or sentence, using the translation you provide in the dictionary. Dictionaries are sometimes called glossaries or term bases. You can think of the dictionary as a brute force "copy and replace" for all the terms you list. Furthermore, Custom translation service builds and makes use of its own general purpose dictionaries to improve the quality of its translation. However, a customer provided dictionary takes precedent and is searched first to look up words or sentences.
+A custom translation dictionary is an aligned pair of documents that specifies a list of phrases or sentences and their corresponding translations. Use a dictionary in your training, when you want Custom Translator to translate any instances of the source phrase or sentence, using the translation you provide in the dictionary. Dictionaries are sometimes called glossaries or term bases. You can think of the dictionary as a brute force "copy and replace" for all the terms you list. Furthermore, Custom translation service builds and makes use of its own general purpose dictionaries to improve the quality of its translation. However, a customer provided dictionary takes precedent and is searched first to look up words or sentences.
 
 Dictionaries only work for projects in language pairs that have a fully supported Microsoft general neural network model behind them. [View the complete list of languages](../../../language-support.md).
 
@@ -38,8 +38,10 @@ A sentence dictionary is case-insensitive. The sentence dictionary allows you to
 
 You can train a model using only dictionary data. To do so, select only the dictionary document (or multiple dictionary documents) that you wish to include and select **Create model**. Since this training is dictionary-only, there's no minimum number of training sentences required. Your model typically completes training faster than a standard training. The resulting models use the Microsoft baseline models for translation with the addition of the dictionaries you add. You don't get a test report.
 
->[!NOTE]
->Custom Translator doesn't sentence align dictionary files, so it is important that there are an equal number of source and target phrases/sentences in your dictionary documents and that they are precisely aligned.
+> [!NOTE]
+> Custom Translator doesn't perform sentence alignment for dictionary files. Therefore, it's crucial to ensure that your dictionary documents contain an equal number of phrases or sentences for both the source and target languages. These phrases or sentences must be carefully and accurately aligned to maintain consistency and effectiveness.
+
+
 
 ## Recommendations
 

articles/ai-services/translator/custom-translator/azure-ai-foundry/concepts/workspace-and-project.md

@@ -16,7 +16,7 @@ ms.custom: cogserv-non-critical-translator
 
 A project is a work area for composing and building your custom translation system. A project can contain multiple language pairs, models, and documents. All the work you do in Custom translation is inside a specific project.
 
-project is private to you and the people you invite into your project. Uninvited people don't have access to the content of your project. You can invite as many people as you like into your project and modify or remove their access anytime. You can also create a new project. By default a project doesn't contain any language pairs or documents that already exist in other projects.
+A project is private to you and the people you invite into your project. Uninvited people don't have access to the content of your project. You can invite as many people as you like into your project and modify or remove their access anytime. You can also create a new project. By default a project doesn't contain any language pairs or documents that already exist in other projects.
 
 ## What is a Custom translation language pair?
 
@@ -35,13 +35,13 @@ In the same project, you can create language pairs for the same language pair in
 Custom translation allows you to assign a label to your language pair. The language pair label distinguishes between multiple language pairs with the same language
 pair and category. As a best practice, avoid using language pair labels unless necessary.
 
-The language pair label is used as part of the **Category ID**. If the language pair label is left unset or is set identically across language pairs, then language pairs with the same category and *different* language pairs share the same Category ID. This approach is advantageous because it allows you to switch between languages when using the  Translator API without worrying about a Category ID that is unique to each language pair.
+The language pair label is used as part of the **Category ID**. When the language pair label is either unspecified or identical for multiple language pairs, those pairs with the same category but *distinct* language combinations share the same Category ID. This method offers a significant benefit by enabling seamless transitions between languages while utilizing the Translator API. Unlike traditional systems, there's no need to manage a separate Category ID for each language pair, simplifying the process considerably and enhancing efficiency.
 
 For example, if I wanted to enable translations in the Technology domain from English-to-French and from French-to-English, I would create two
 language pairs: one for English -\> French, and one for French -\> English. I would specify the same category (Technology) for both and leave the project label
 blank. The Category ID for both language pairs would match, so I could query the API for both English and French translations without having to modify my Category ID.
 
-If you're a language service provider and want to serve multiple customers with different models that retain the same category and language pair, use a language pair label to differentiate between customers.
+For language service providers aiming to cater to multiple customers with models that share the same category and language pair, applying a language pair label is an effective way to distinguish between different clients. This approach ensures clarity and organization when managing customer-specific models within identical language pairings.
 
 ## Next steps
 

articles/ai-services/translator/custom-translator/azure-ai-foundry/how-to/copy-model.md

@@ -18,9 +18,9 @@ Copying a model to other project enables model lifecycle management (for example
 
    > [!NOTE]
    >
-   > To copy model from one project to another, you must be a user with an **Owner** role in both projects .
+   > To copy model from one project to another, you must be a user with an **Owner** role in both projects.
    >
-   > The copied model cannot be recopied. You can only rename, delete, or publish a copied model.
+   > The copied model can't be recopied. You can only rename, delete, or publish a copied model.
 
 1. After successful model training, select the **Train model** from the left menu.
 

articles/ai-services/translator/custom-translator/azure-ai-foundry/how-to/create-language-pair.md

@@ -12,7 +12,7 @@ ms.topic: how-to
 
 # Create language pair
 
-A language pair includes models, training, tuning and testing datasets. Creating a language pair is the first step in fine-tuning and deploying a model.
+A language pair includes models, training, tuning, and testing datasets. Creating a language pair is the first step in fine-tuning and deploying a model.
 
 ## Create a language pair
 
@@ -29,7 +29,7 @@ A language pair includes models, training, tuning and testing datasets. Creating
     :::image type="content" source="../media/fine-tune-create-language-pair.png" alt-text="Screenshot of dialog to create a language pair and fill out the details.":::
 
    > [!NOTE]
-   > Select **Advanced options** to add optional details, e.g., label, language pair description, and domain description.
+   > Select **Advanced options** to add optional details, for example, label, language pair description, and domain description.
 
    - **Language pair label:** You can add label to create the same language pair multiple times. Example, you want to create English to French model for shopping and another English to French model for automotive. A label distinguishes between the same language pair with the same language pair and domain. As a best practice, here are a few tips:
 

articles/ai-services/translator/custom-translator/azure-ai-foundry/how-to/create-project.md

@@ -17,7 +17,7 @@ ms.topic: how-to
 
 ## Create a project
 
-In the [Azure AI Foundry portal](https://ai.azure.com/), you can fine-tune some Azure AI services models, e.g., Custom translation, Custom speech, etc. For Custom translation, you can fine-tune a model for a language pair, *say* English to French.
+In the [Azure AI Foundry portal](https://ai.azure.com/), you can fine-tune some Azure AI services models, for example, Custom translation, Custom speech, etc. For Custom translation, you can fine-tune a model for a language pair, *say* English to French.
 
 1. Go to your project in the [Azure AI Foundry portal](https://ai.azure.com/) portal. If you need to create a project, *see* [Create an Azure AI Foundry project](../../azure-ai-foundry/how-to/create-project.md).
 

articles/ai-services/translator/custom-translator/azure-ai-foundry/how-to/deploy-model.md

@@ -17,7 +17,7 @@ Deploying your Custom translation model makes it available for use with the Azur
 
 You can deploy one model per language pair to one or multiple regions.
 
-1. Select the **Deploy model** from the menu on the left.
+1. Select **Deploy model** from the menu on the left.
 
 1. Select the model name under **Name** and check the button then select **Deploy model**.
 
@@ -39,11 +39,11 @@ To replace a deployed model, you can exchange the deployed model with a differen
 
 1. Select **Swap model**.
 
-The redeployment takes several minutes to complete. In the meantime, deployed model will continue to be available for use with the Translator API until this process is complete.
+   The redeployment takes several minutes to complete. In the meantime, deployed model continues to be available for use with the Translator API until this process is complete.
 
    :::image type="content" source="../media/fine-tune-swap-model-2.png" alt-text="Screenshot illustrating the swap-model function.":::
 
 ## Next steps
 
 > [!div class="nextstepaction"]
-> [Learn how to Translate using your deployed model](translate-from-model.md)
+> [Learn how to Translate using your deployed model](translate-with-model.md)

articles/ai-services/translator/custom-translator/azure-ai-foundry/how-to/test-model.md

@@ -23,7 +23,7 @@ A BLEU score is a number between zero and 100. A score of zero indicates a low-q
 
 ## Test quality of your model's translation
 
-1. Select **Test model** from the left menue.
+1. Select **Test model** from the left menu.
 
 1. Select model **Name** then select **View test results**.
 

articles/ai-services/translator/custom-translator/azure-ai-foundry/how-to/train-model.md

@@ -43,10 +43,10 @@ Custom translation model provides translations for a specific language pair. The
 
 ## When to select dictionary-only training
 
-For better results, we recommended letting the system learn from your training data. However, when you don't have enough parallel sentences to meet the 10,000 minimum requirements, and sentences and compound nouns must be rendered as-is, use dictionary-only training. Your model typically completes training faster than with full training. The resulting models use the baseline models for translation along with the dictionaries you added. You will not see `BLEU` scores and test report.
+For better results, we recommended letting the system learn from your training data. However, when you don't have enough parallel sentences to meet the 10,000 minimum requirements, and sentences and compound nouns must be rendered as-is, use dictionary-only training. Your model typically completes training faster than with full training. The resulting models use the baseline models for translation along with the dictionaries you added. You don't see `BLEU` scores and test report.
 
 > [!NOTE] 
->Custom translation doesn't sentence-align dictionary files. Therefore, it is important that there are an equal number of source and target phrases/sentences in your dictionary documents and that they are precisely aligned. If not, the document upload will fail.
+>Custom translation doesn't sentence-align dictionary files. Therefore, it's important that there are an equal number of source and target phrases/sentences in your dictionary documents and that they're precisely aligned. If not, the document upload fails.
 
 ## Model details
 

articles/ai-services/translator/custom-translator/azure-ai-foundry/how-to/translate-from-model.md renamed to articles/ai-services/translator/custom-translator/azure-ai-foundry/how-to/translate-with-model.md

@@ -29,4 +29,4 @@ The following table presents a list of key terms that you may find as you work w
 | Testing Files| These files are often derived files, randomly selected from the training set (if you don't select any test set). The purpose of these sentences is to evaluate the translation model's accuracy. To make sure the system accurately translates these sentences, you may wish to create a testing set and upload it to the translator. Doing so ensures that the sentences are used in the system's evaluation (the generation of a `BLEU` score).   |
 | Combo file   | A type of file in which the source and translated sentences are contained in the same file. Supported file formats (`TMX`, `XLIFF`, `XLF`, `ICI`, and `XLSX`). |
 | Archive file | A file that contains other files. Supported file formats (zip, gz, tgz).  |
-| `BLEU` Score   | [BLEU](concepts/bleu-score.md) is the industry standard method for evaluating the "precision" or accuracy of the translation model. Though other methods of evaluation exist, Microsoft Translator relies BLEU  method to report accuracy to Project Owners.
+| `BLEU` Score   | [`BLEU`](concepts/bleu-score.md) is the industry standard method for evaluating the "precision" or accuracy of the translation model. Though other methods of evaluation exist, Microsoft Translator relies `BLEU`  method to report accuracy to Project Owners.|