Merge pull request #76376 from diberry/0510-qna-chitchat

[Cogsvcs] QnA Maker - chit chat personalities

Author: rjagiewich

articles/cognitive-services/QnAMaker/Concepts/best-practices.md

@@ -8,7 +8,7 @@ manager: nitinme
 ms.service: cognitive-services
 ms.subservice: qna-maker
 ms.topic: article
-ms.date: 03/28/2019
+ms.date: 05/10/2019
 ms.author: tulasim
 ms.custom: seodec18
 ---
@@ -34,18 +34,20 @@ Add as many alternate questions as you need but keep the alterations simple. Add
 The best answers are simple answers but not too simple such as yes and no answers. If your answer should link to other sources or provide a rich experience with media and links, use [tagging](../how-to/metadata-generateanswer-usage.md) to distinguish which type of answer you expect, then submit that tag with the query to get the correct answer version.
 
 ## Chit-Chat
-Add chit-chat to your bot, to make your bot more conversational and engaging, with low effort. You can easily add chit-chat data sets for 3 pre-defined personalities when creating your KB, and change them at any time. Learn how to [add chit-chat to your KB](../How-To/chit-chat-knowledge-base.md). 
+Add chit-chat to your bot, to make your bot more conversational and engaging, with low effort. You can easily add chit-chat data sets from pre-defined personalities when creating your KB, and change them at any time. Learn how to [add chit-chat to your KB](../How-To/chit-chat-knowledge-base.md). 
 
 ### Choosing a personality
-Chit-chat is supported for 3 predefined personalities: 
+Chit-chat is supported for several predefined personalities: 
 
-|Personalities|
-|--|
-|The Professional|
-|The Friend|
-|The Comic|
+|Personality |QnA Maker Dataset file |
+|---------|-----|
+|Professional |[qna_chitchat_professional.tsv](https://qnamakerstore.blob.core.windows.net/qnamakerdata/editorial/qna_chitchat_professional.tsv) |
+|Friendly |[qna_chitchat_friendly.tsv](https://qnamakerstore.blob.core.windows.net/qnamakerdata/editorial/qna_chitchat_friendly.tsv) |
+|Witty |[qna_chitchat_witty.tsv](https://qnamakerstore.blob.core.windows.net/qnamakerdata/editorial/qna_chitchat_witty.tsv) |
+|Caring |[qna_chitchat_caring.tsv](https://qnamakerstore.blob.core.windows.net/qnamakerdata/editorial/qna_chitchat_caring.tsv) |
+|Enthusiastic |[qna_chitchat_enthusiastic.tsv](https://qnamakerstore.blob.core.windows.net/qnamakerdata/editorial/qna_chitchat_enthusiastic.tsv) |
 
-The responses range from formal to informal and irreverent. You should select the personality that is closest aligned with the tone you want for your bot. You can view the datasets, and choose one that serves as a base for your bot, and then customize the responses. 
+The responses range from formal to informal and irreverent. You should select the personality that is closest aligned with the tone you want for your bot. You can view the [datasets](https://github.com/Microsoft/BotBuilder-PersonalityChat/tree/master/CSharp/Datasets), and choose one that serves as a base for your bot, and then customize the responses. 
 
 ### Edit bot-specific questions
 There are some bot-specific questions that are part of the chit-chat data set, and have been filled in with generic answers. Change these answers to best reflect your bot details. 

articles/cognitive-services/QnAMaker/How-To/chit-chat-knowledge-base.md

@@ -8,7 +8,7 @@ manager: nitinme
 ms.service: cognitive-services
 ms.subservice: qna-maker
 ms.topic: article
-ms.date: 05/07/2019
+ms.date: 05/10/2019
 ms.author: tulasim
 ms.custom: seodec18
 ---
@@ -19,17 +19,19 @@ Adding chit-chat to your bot makes it more conversational and engaging. The chit
 
 This dataset has about 100 scenarios of chit-chat in the voice of multiple personas, like Professional,Friendly and Witty. Choose the persona that most closely resembles your bot's voice. Given a user query, QnA Maker tries to match it with the closest known chit-chat QnA.  
 
-Some examples of the different personalities are below. You can see all the personality datasets along with details of the personalities [here](https://github.com/Microsoft/BotBuilder-PersonalityChat/tree/master/CSharp/Datasets).
-
-<!-- added quotes so acrolinx doesn't score these sentences -->
-|User query|Professional|Friendly|Witty|
-|--|--|--|--|
-|`You are awesome`|`I aim to serve.`|`Aw, I'm blushing.`|`Flattery. I like it.`|
-|`Are you hungry?`|`I don't need to eat.`|`I only do food for thought.`|`Eating would require a lot of things I don't have. Like a digestive system. And silverware.`|
-|`Sing a song`|`I'm afraid I'm not musically inclined.`|`La la la, tra la la. I'm awesome at this.`|`Those who can, do. Those who can't, don't sing.`|
-|`Will you marry me?`|`I think it's best if we stick to a professional relationship.`|`Definitely didn't see that coming!`|`Sure. Take me to city hall. See what happens.`|
+Some examples of the different personalities are below. You can see all the personality [datasets](https://github.com/Microsoft/BotBuilder-PersonalityChat/tree/master/CSharp/Datasets) along with details of the personalities.
 
+For the user query of `When is your birthday?`, each personality has a styled response:
 
+<!-- added quotes so acrolinx doesn't score these sentences -->
+|Personality|Example|
+|--|--|
+|Professional|Age doesn't really apply to me.|
+|Friendly|I don't really have an age.|
+|Witty|I'm age-free.|
+|Caring|I don't have an age.|
+|Enthusiastic|I'm a bot, so I don't have an age.|
+||
 
 > [!NOTE]
 > Chit-chat support is currently available in English only.