update what's new?

Author: laujan

articles/applied-ai-services/form-recognizer/whats-new.md

@@ -44,7 +44,7 @@ Form Recognizer service is updated on an ongoing basis. Bookmark this page to st
   * [**Formula extraction**](concept-add-on-capabilities.md#formula-extraction) is now recognized with the ```2023-02-28-preview``` API.
   * [**High resolution extraction**](concept-add-on-capabilities.md#high-resolution-extraction) is now recognized with the ```2023-02-28-preview``` API.
 * [**Common name key normalization**](concept-general-document.md#key-normalization-common-name) capabilities are added to the General Document model to improve processing forms with variations in key names. 
-* **Custom extraction model updates**
+* [**Custom extraction model updates**](concept-custom.md)
   * [**Custom neural model**](concept-custom-neural.md) now supports added languages for training and analysis. Train neural models for Dutch, French, German, Italian and Spanish.
   * [**Custom template model**](concept-custom-template.md) now has an improved signature detection capability.
 * [**Form Recognizer Studio**](https://formrecognizer.appliedai.azure.com/studio) updates
@@ -884,7 +884,7 @@ Form Recognizer service is updated on an ongoing basis. Bookmark this page to st
 
 * **Form Recognizer v2.1-preview.1 has been released and includes the following features:
 
-  * **REST API reference is available** - View the [`v2.1-preview.1 reference`](https://westcentralus.dev.cognitive.microsoft.com/docs/services/form-recognizer-api-v2-1-preview-1/operations/AnalyzeBusinessCardAsync)
+  * **REST API reference is available** - View the [`v2.1-preview.1 reference`](https://westus.dev.cognitive.microsoft.com/docs/services/form-recognizer-api-v2-1/operations/AnalyzeBusinessCardAsync)
   * **New languages supported In addition to English**, the following [languages](language-support.md) are now supported: for `Layout` and `Train Custom Model`: English (`en`), Chinese (Simplified) (`zh-Hans`), Dutch (`nl`), French (`fr`), German (`de`), Italian (`it`), Portuguese (`pt`) and Spanish (`es`).
   * **Checkbox / Selection Mark detection** – Form Recognizer supports detection and extraction of selection marks such as check boxes and radio buttons. Selection Marks are extracted in `Layout` and you can now also label and train in `Train Custom Model` - _Train with Labels_ to extract key-value pairs for selection marks.
   * **Model Compose** - allows multiple models to be composed and called with a single model ID. When you submit a document to be analyzed with a composed model ID, a classification step is first performed to route it to the correct custom model. Model Compose is available for `Train Custom Model` - _Train with labels_.