Merge pull request #102065 from diberry/diberry/0123-luis-active-learning

[Cogsvcs] LUIS - log=true

Author: v-shils

articles/cognitive-services/LUIS/luis-concept-review-endpoint-utterances.md

@@ -9,30 +9,34 @@ ms.custom: seodec18
 ms.service: cognitive-services
 ms.subservice: language-understanding
 ms.topic: conceptual
-ms.date: 10/10/2019
+ms.date: 01/23/2020
 ms.author: diberry
 ---
 # Concepts for enabling active learning by reviewing endpoint utterances
 Active learning is one of three strategies to improve prediction accuracy and the easiest to implement. With active learning, your review endpoint utterances for correct intent and entity. LUIS chooses endpoint utterances it is unsure of.
 
 ## What is active learning
-Active learning is a two-step process. First, LUIS selects utterances it receives at the app's endpoint that need validation. The second step is performed by the app owner or collaborator to validate the selected utterances for [review](luis-how-to-review-endpoint-utterances.md), including the correct intent and any entities within the intent. After reviewing the utterances, train and publish the app again. 
+Active learning is a two-step process. First, LUIS selects utterances it receives at the app's endpoint that need validation. The second step is performed by the app owner or collaborator to validate the selected utterances for [review](luis-how-to-review-endpoint-utterances.md), including the correct intent and any entities within the intent. After reviewing the utterances, train and publish the app again.
 
 ## Which utterances are on the review list
-LUIS adds utterances to the review list when the top firing intent has a low score or the top two intents' scores are too close. 
+LUIS adds utterances to the review list when the top firing intent has a low score or the top two intents' scores are too close.
 
 ## Single pool for utterances per app
-The **Review endpoint utterances** list doesn't change based on the version. There is a single pool of utterances to review, regardless of which version the utterance you are actively editing or which version of the app was published at the endpoint. 
+The **Review endpoint utterances** list doesn't change based on the version. There is a single pool of utterances to review, regardless of which version the utterance you are actively editing or which version of the app was published at the endpoint.
 
 ## Where are the utterances from
-Endpoint utterances are taken from end-user queries on the application’s HTTP endpoint. If your app is not published or has not received hits yet, you do not have any utterances to review. If no endpoint hits are received for a specific intent or entity, you do not have utterances to review that contain them. 
+Endpoint utterances are taken from end-user queries on the application’s HTTP endpoint. If your app is not published or has not received hits yet, you do not have any utterances to review. If no endpoint hits are received for a specific intent or entity, you do not have utterances to review that contain them.
 
 ## Schedule review periodically
-Reviewing suggested utterances doesn't need to be done every day but should be part of your regular maintenance of LUIS. 
+Reviewing suggested utterances doesn't need to be done every day but should be part of your regular maintenance of LUIS.
 
 ## Delete review items programmatically
 Use the **[delete unlabeled utterances](https://westus.dev.cognitive.microsoft.com/docs/services/5890b47c39e2bb17b84a55ff/operations/58b6f32139e2bb139ce823c9)** API. Back up these utterances before deletion by **[exporting the log files](https://westus.dev.cognitive.microsoft.com/docs/services/5890b47c39e2bb17b84a55ff/operations/5890b47c39e2bb052c5b9c36)**.
 
+## Enable active learning
+
+To enable active learning, you must log user queries. This is accomplished by calling the [endpoint query](luis-get-started-create-app.md#query-the-v3-api-prediction-endpoint) with the `log=true` querystring parameter and value.
+
 ## Next steps
 
 * Learn how to [review](luis-how-to-review-endpoint-utterances.md) endpoint utterances

articles/cognitive-services/LUIS/luis-how-to-review-endpoint-utterances.md

@@ -9,7 +9,7 @@ ms.custom: seodec18
 ms.service: cognitive-services
 ms.subservice: language-understanding
 ms.topic: conceptual
-ms.date: 12/17/2019
+ms.date: 01/23/2020
 ms.author: diberry
 ---