Merge pull request #108382 from diberry/diberry/0319-qna-active-learning-default

[Cogsvcs] QnA Maker - Active Learning setting defa

Author: PRMerger12

articles/cognitive-services/QnAMaker/Concepts/active-learning-suggestions.md

@@ -2,7 +2,7 @@
 title: Active learning suggestions - QnA Maker
 description: Active learning suggestions allows you to improve the quality of your knowledge base by suggesting alternative questions, based on user-submissions, to your question and answer pair.
 ms.topic: conceptual
-ms.date: 02/27/2020
+ms.date: 03/19/2020
 ---
 # Active learning suggestions
 
@@ -27,6 +27,13 @@ Active learning gives the best possible suggestions in cases where the endpoints
 
 Once questions are suggested in the QnA Maker portal, you need to review and accept or reject those suggestions. There isn't an API to manage suggestions.
 
+## Turn on active learning
+
+By default, active learning is **off**.
+To use active learning:
+* You need to [turn on active learning](../How-To/use-active-learning.md#turn-on-active-learning-for-alternate-questions) so that QnA Maker collects alternate questions for your knowledge base.
+* To see the suggested alternate questions, [use View options](../How-To/improve-knowledge-base.md#view-suggested-questions) on the Edit page.
+
 ## How QnA Maker's implicit feedback works
 
 QnA Maker's implicit feedback uses an algorithm to determine score proximity then makes active learning suggestions. The algorithm to determine proximity is not a simple calculation. The ranges in the following example are not meant to be fixed but should be used as a guide to understand the impact of the algorithm only.