resolve feedback

Author: laujan

articles/applied-ai-services/form-recognizer/compose-custom-models-preview.md

@@ -75,11 +75,7 @@ If you want to use manually labeled data, you'll also have to upload the *.label
 
 ## Train your custom model
 
-You can [train your model](https://formrecognizer.appliedai.azure.com/studio/custommodel/projects)  with or without labeled data sets. Unlabeled datasets rely solely on the [prebuilt-layout model](https://westus.dev.cognitive.microsoft.com/docs/services/form-recognizer-api-v3-0-preview-2/operations/AnalyzeDocument) to detect and identify key information without added human input. Labeled datasets also rely on the Layout API, but supplementary human input is included such as your specific labels and field locations. To use both labeled and unlabeled data, start with at least five completed forms of the same type for the labeled training data and then add unlabeled data to the required data set.
-
-### Train without labels
-
-Form Recognizer uses unsupervised learning to understand the layout and relationships between fields and entries in your forms. When you submit your input forms, the algorithm clusters the forms by type, discovers what keys and tables are present, and associates values to keys and entries to tables. Training without labels doesn't require manual data labeling or intensive coding and maintenance, and we recommend you try this method first.
+You [train your model](https://formrecognizer.appliedai.azure.com/studio/custommodel/projects). Labeled datasets rely on the prebuilt-layout API, but supplementary human input is included such as your specific labels and field locations. To use both labeled data, start with at least five completed forms of the same type for the labeled training data and then add unlabeled data to the required data set.
 
 ### Train with labels
 

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

@@ -121,7 +121,7 @@ https://{endpoint}/formrecognizer/documentModels:build?api-version=2022-01-30-pr
   > [!div class="nextstepaction"]
   > [Form Recognizer quickstart](quickstarts/try-v3-form-recognizer-studio.md#custom-models)
 
-* View the labeling guidelines:
+* View the REST API:
 
     > [!div class="nextstepaction"]
     > [Form Recognizer API v3.0](https://westus.dev.cognitive.microsoft.com/docs/services/form-recognizer-api-v3-0-preview-2/operations/AnalyzeDocument)

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

@@ -69,7 +69,7 @@ https://{endpoint}/formrecognizer/documentModels:build?api-version=2022-01-30-pr
   > [!div class="nextstepaction"]
   > [Custom neural models](concept-custom-neural.md )
 
-* View the labeling guidelines:
+* View the REST API:
 
     > [!div class="nextstepaction"]
     > [Form Recognizer API v2.1](https://westus.dev.cognitive.microsoft.com/docs/services/form-recognizer-api-v2-1/operations/AnalyzeWithCustomForm)

articles/applied-ai-services/form-recognizer/quickstarts/try-v3-csharp-sdk.md

@@ -48,22 +48,22 @@ items:
     href: how-to-guides/try-sdk-rest-api.md
   - name: Generate SAS tokens for Azure Blob containers
     href:  generate-sas-tokens.md
-  - name: Create and compose custom models v2.1
+  - name: Custom models
     items:
-    - name: Build and train custom models
-      items:
-      - name: Assemble a training data set
-        href: build-training-data-set.md
-      - name:   Deploy the sample-labeling tool
-        href: deploy-label-tool.md
-      - name: Train a custom model with the sample-labeling tool
-        href: label-tool.md
-      - name: Use table tags to train your custom model
-        href: supervised-table-tags.md
-      - name: Compose custom models v3.0 (preview)
-        href: compose-custom-models-preview.md
-      - name: Compose custom models v2.1 (GA)
-        href: compose-custom-models.md   
+    - name: Assemble a training data set
+      href: build-training-data-set.md
+    - name:   Deploy the sample-labeling tool
+      href: deploy-label-tool.md
+    - name: Train a custom model with the sample-labeling tool
+      href: label-tool.md
+    - name: Use table tags to train your custom model
+      href: supervised-table-tags.md
+  - name: Composed models
+    items:
+     - name: Compose models v3.0 (preview)
+       href: compose-custom-models-preview.md
+     - name: Compose models v2.1 (GA)
+       href: compose-custom-models.md
   - name: Back up and recover models
     href: disaster-recovery.md
   - name: Use containers
@@ -132,15 +132,17 @@ items:
     href: concept-id-document.md
   - name: Business card model
     href: concept-business-card.md
-  - name: Custom model
-    href: concept-custom.md
-  - name: Custom template model 
-    href: concept-custom-template.md 
-  - name: Custom neural model
-    href: concept-custom-neural.md 
-  - name: "Custom models: accuracy and confidence scores"
-    href: concept-accuracy-confidence.md
-  - name: "Composed custom models"
+  - name: Custom models
+    items:  
+    - name: Custom model
+      href: concept-custom.md
+    - name: Custom template model
+      href: concept-custom-template.md
+    - name: Custom neural model
+      href: concept-custom-neural.md
+    - name: Accuracy and confidence scores
+      href: concept-accuracy-confidence.md
+  - name: Composed models
     href:  concept-composed-models.md
 - name: Tutorials
   items:

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

@@ -22,7 +22,7 @@ Form Recognizer v3.0 (preview) introduces several new features and capabilities:
 
 * [Form Recognizer REST API](quickstarts/try-v3-rest-api.md) has been redesigned for better usability.
 * [**General document (v3.0)**](concept-general-document.md) model is a new API that extracts text, tables, structure, key-value pairs, and named entities from forms and documents.
-* [**Custom document model (v3.0)**](concept-custom-document.md) is a new custom model type to extract fields from structured and unstructured documents.
+* [**Custom document model (v3.0)**](concept-custom-neural.md) is a new custom model type to extract fields from structured and unstructured documents.
 * [**Receipt (v3.0)**](concept-receipt.md) model supports single-page hotel receipt processing.
 * [**ID document (v3.0)**](concept-id-document.md) model supports endorsements, restrictions, and vehicle classification extraction from US driver's licenses.
 * [**Custom model API (v3.0)**](concept-custom.md) supports signature detection for custom forms.

articles/applied-ai-services/form-recognizer/v3-migration-guide.md

@@ -23,10 +23,13 @@ Form Recognizer service is updated on an ongoing basis. Bookmark this page to st
 
  Form Recognizer v3.0 preview release introduces several new features and capabilities and enhances existing one:
 
-* [**Read**](concept-read.md) API extracts text lines, words, their locations, detected languages, and handwritten style if detected.  
-* [**Language Expansion**](language-support.md) Form Recognizer Read, Layout, and Custom Form add support for 42 new languages including Arabic, Hindi, and other languages using Arabic and Devanagari scripts to expand the coverage to 164 languages. Handwritten support for the same features expands to Japanese and Korean in addition to English, Chinese Simplified, French, German, Italian, Portuguese, and Spanish languages.
 * [**Form Recognizer Studio**](https://formrecognizer.appliedai.azure.com) adds new demos for Read, W2, Hotel receipt samples, and support for training the new custom neural models.
+* [🆕 **W-2 prebuilt model**](concept-w2.md) is a new prebuilt model to extract fields from W-2 tax documents.
+* [🆕 **Read**](concept-read.md) API extracts text lines, words, their locations, detected languages, and handwritten style if detected.  
+* [🆕 **Custom neural model**](concept-custom-neural.md) is a new custom model to extract text and selection marks from structured forms and **unstructured documents**.
+* [**Language Expansion**](language-support.md) Form Recognizer Read, Layout, and Custom Form add support for 42 new languages including Arabic, Hindi, and other languages using Arabic and Devanagari scripts to expand the coverage to 164 languages. Handwritten support for the same features expands to Japanese and Korean in addition to English, Chinese Simplified, French, German, Italian, Portuguese, and Spanish languages.
 * [**Invoice API**](language-support.md#invoice-model) Invoice API expands support to Spanish invoices.
+* [**General document**](concept-general-document.md) pre-trained model now updated to support selection marks in addition to API  text, tables, structure, key-value pairs, and named entities from forms and documents.
 
 Get stared with the new [REST API](https://westus.dev.cognitive.microsoft.com/docs/services/form-recognizer-api-v3-0-preview-2/operations/AnalyzeDocument), [Python](quickstarts/try-v3-python-sdk.md), or [.NET](quickstarts/try-v3-csharp-sdk.md) SDK for the v3.0 preview API.
 
@@ -43,20 +46,6 @@ Get stared with the new [REST API](https://westus.dev.cognitive.microsoft.com/do
   | Business card    | ✓  |   ✓ |   |   ||
   | Custom             |✓  |  ✓ | ✓  | ✓  | ✓  |
 
-### Form Recognizer v3.0 preview update 2
-
-* [**Custom document**](concept-custom-neural.md ) model is a new custom model to extract text and selection marks from structured forms and **unstructured documents**.
-
-* [**W-2 prebuilt model**](concept-w2.md) is a new prebuilt model to extract fields from W-2 tax documents.
-
-* [**General document**](concept-general-document.md) pre-trained model now updated to support selection marks in addition to API  text, tables, structure, key-value pairs, and named entities from forms and documents.
-
-* [**Spanish language invoices**](concept-invoice.md) model adds support for Spanish language invoices.
-
-* Read API, Form Recognizer customers can now call the Read API from Form Recognizer.
-
-* [Expanded language support](language-support.md) With this preview, Read, Layout and Custom form now support 164 languages for print text including Russian, Hindi and Arabic and similar regional languages. The preview also expands the handwritten support to Japanese and Korean resulting in a total of 9 supported languages.
-
 ## November 2021
 
 ### Form Recognizer v3.0 preview SDK release update (beta.2)