edit for pub

Author: laujan

articles/applied-ai-services/form-recognizer/concept-custom-label-tips.md

@@ -17,17 +17,13 @@ recommendations: false
 
 This article highlights the best methods for labeling custom model datasets in the Form Recognizer Studio. Labeling documents can be time consuming when you have a large number of labels, long documents, or documents with varying structure. These tips should help you label documents more efficiently.
 
-## Video: Custom labels best practices (part two)
+## Video: Custom labels best practices
 
-The following is the second of two videos intended to help you build custom
-models with higher accuracy.
+* The following video is the second of two presentations intended to help you build custom models with higher accuracy (the first presentation explores [How to create a balanced data set](concept-custom-label.md#video-custom-label-tips-and-pointers)).
 
-* This video, explores the best practices for labeling your selected documents. With consistent labeling and following these best practices, you
-should see an improvement in model performance.
+* Here, we'll examine best practices for labeling your selected documents. With consistent labeling and following these suggestions, you should see an improvement in model performance.
 
-> [!VIDEO https://www.microsoft.com/en-us/videoplayer/embed/RE5fZKB ]
-
-* The first video (part one) explores [How to create a balanced data set](concept-custom-label.md#video-custom-label-tips-and-pointers-part-one).
+  > [!VIDEO https://www.microsoft.com/en-us/videoplayer/embed/RE5fZKB ]
 
 ## Search
 

articles/applied-ai-services/form-recognizer/concept-custom-label.md

@@ -32,24 +32,21 @@ A labeled dataset consists of several files:
 
   * A `{file}.labels.json` file is created or updated when a field is labeled in a document. The label file contains the spans of text and associated polygons from the layout output for each span of text the user adds as a value for a specific field.
 
-## Video: Custom label tips and pointers (part one)
+## Video: Custom label tips and pointers
 
-The following is the first of two videos intended to help you build custom
-models with higher accuracy.
+* The following video is the first of two presentations intended to help you build custom models with higher accuracy (The second presentation examines [Best practices for labeling documents](concept-custom-label-tips.md#video-custom-labels-best-practices)).
 
-* This video (part one), explores how to create a balanced data set and select the right documents to label. The process will set you on the path to a higher quality model.
+* Here, we'll explore how to create a balanced data set and select the right documents to label. This process will set you on the path to higher quality models.
 
-> [!VIDEO https://www.microsoft.com/en-us/videoplayer/embed/RWWHru]
-
-* The second video (part two), presents the [Best practices for labeling documents](concept-custom-label-tips.md#video-custom-labels-best-practices).
+  > [!VIDEO https://www.microsoft.com/en-us/videoplayer/embed/RWWHru]
 
 ## Create a balanced dataset
 
 Before you start labeling, it's a good idea to look at a few different samples of the document to identify which samples you want to use in your labeled dataset. A balanced dataset represents all the typical variations you would expect to see for the document. Creating a balanced dataset will result in a model with the highest possible accuracy. A few examples to consider are:
 
 * **Document formats**: If you expect to analyze both digital and scanned documents, add a few examples of each type to the training dataset
 
-* **Variations (template model)**:  Consider splitting the dataset into folders and train a model for each of variation. Variations that include either structure or layout should be split into different models. You can then compose the individual models into a single [composed model](concept-composed-models.md).
+* **Variations (template model)**:  Consider splitting the dataset into folders and train a model for each of variation. Any variations that include either structure or layout should be split into different models. You can then compose the individual models into a single [composed model](concept-composed-models.md).
 
 * **Variations (Neural models)**: When your dataset has a manageable set of variations, about 15 or fewer, create a single dataset with a few samples of each of the different variations to train a single model. If the number of template variations is larger than 15, you'll train multiple models and [compose](concept-composed-models.md) them together.
 

articles/applied-ai-services/form-recognizer/how-to-guides/build-a-custom-model.md

@@ -48,9 +48,9 @@ Once you've put together the set of forms or documents for training, you'll need
 
 ## Video: Train your custom model
 
-Once you've gathered and uploaded your training dataset, you're ready to train your custom model. In the following video, we'll create a project and explore come of the fundamentals for labeling and training a model:
+Once you've gathered and uploaded your training dataset, you're ready to train your custom model. In the following video, we'll create a project and explore some of the fundamentals for labeling and training a model:
 
-> [VIDEO https://www.microsoft.com/en-us/videoplayer/embed/RE5fX1c]
+  > [VIDEO https://www.microsoft.com/en-us/videoplayer/embed/RE5fX1c]
 
 ## Create a project in the Form Recognizer Studio
 

articles/applied-ai-services/form-recognizer/overview.md

@@ -34,9 +34,9 @@ Azure Form Recognizer is a cloud-based [Azure Applied AI Service](../../applied-
 
 ## Video: Form Recognizer models
 
-The following video introduces the Form Recognizer models and their associated output to help you choose which one is best to address your document scenario needs.
+The following video introduces Form Recognizer models and their associated output to help you choose which one is best to address your document scenario needs.</br></br>
 
-> [!VIDEO https://www.microsoft.com/en-us/videoplayer/embed/RE5fX1b]
+  > [!VIDEO https://www.microsoft.com/en-us/videoplayer/embed/RE5fX1b]
 
 ## Which Form Recognizer model should I use?
 

articles/applied-ai-services/form-recognizer/toc.yml

@@ -171,10 +171,10 @@ items:
     - name: Custom neural model
       displayName: selection, structure, tables, tabular, train, template, neural, build mode, signatures, custom
       href: concept-custom-neural.md
-    - name: Custom labels and datasets
+    - name: Create labeled datasets
       displayName: structure, selection, labels, tables, tabular, train
       href: concept-custom-label.md
-    - name: Custom label tips and pointers
+    - name: Labeling tips and pointers
       displayName: structure, selection, labels, tables, tabular, train, tips
       href: concept-custom-label-tips.md
     - name: Composed models