Skip to content

Commit d2aa1c6

Browse files
committed
edits
1 parent f6cca2c commit d2aa1c6

File tree

1 file changed

+26
-13
lines changed
  • articles/cognitive-services/QnAMaker/Overview

1 file changed

+26
-13
lines changed

articles/cognitive-services/QnAMaker/Overview/overview.md

Lines changed: 26 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -1,24 +1,30 @@
11
---
2-
title: What is QnA Maker API service?
2+
title: What is QnA Maker service?
33
titleSuffix: Azure Cognitive Services
4-
description: QnA Maker is a cloud-based API service that applies custom machine-learning intelligence to a user's natural language question to provide the best answer.
4+
description: QnA Maker is a cloud-based NLP service that easily creates a natural conversational layer over your data. It can be used to find the most appropriate answer for any given natural language input, from your custom knowledge base (KB) of information.
55
services: cognitive-services
6-
author: tulasim88
6+
author: diberry
77
manager: nitinme
88
ms.service: cognitive-services
99
ms.subservice: qna-maker
1010
ms.topic: overview
11-
ms.date: 07/17/2019
12-
ms.author: tulasim
11+
ms.date: 08/01/2019
12+
ms.author: diberry
1313
#customer intent: As a developer, I want to know how to use QnA Maker for my FAQs and product manuals so that I can enable conversational question and answer sessions for my customers.
1414
---
1515

16-
# What is the QnA Maker API service?
16+
# What is the QnA Maker service?
1717

18-
QnA Maker is a cloud-based API service that takes natural language questions, and returns the most appropriate answer from your custom knowledge base (KB) of information.
18+
QnA Maker is a cloud-based NLP service that easily creates a natural conversational layer over your data. It can be used to find the most appropriate answer for any given natural language input, from your custom knowledge base (KB) of information.
1919

2020
A client application for QnA Maker is any conversational application that communicates with a user in natural language to answer a question. Examples of client applications include social media apps, chat bots, and speech-enabled desktop applications.
2121

22+
## When to use QnA Maker
23+
24+
* **When you have static information** - Use QnA Maker when you have a static information in your knowledge base of answers. This knowledge base is custom to your needs, which you've built with documents such as PDFs and URLs.
25+
* **When you want to provide the same answer to a request, question, or command** - when different users submit the same question, the same answer is returned to both.
26+
* **When you want to manage a bot conversation that includes static information** - your knowledge takes a user's conversational text or command and answers it. If the answer is part of a pre-determined conversation flow, represented in your knowledge base with multi-turn context, the bot can easily provide this flow.
27+
2228
## Use QnA Maker knowledge base in a chat bot
2329

2430
Once a QnA Maker knowledge base is published, a client application sends a question to your knowledge base endpoint and receives the results as a JSON response. A common client application for QnA Maker is a chat bot.
@@ -45,13 +51,11 @@ After you publish your knowledge base, a client application sends a user's quest
4551

4652
The QnA Maker portal provides the complete knowledge base authoring experience. You can import documents, in their current form, to your knowledge base. These documents (such as an FAQ, product manual, spreadsheet, or web page) are converted into question and answer sets. Each set is analyzed for follow-up prompts and connected to other sets. The final markdown format supports rich presentation including images.
4753

48-
49-
5054
Once your knowledge base is edited, publish the knowledge base to a working [Azure Web App bot](https://azure.microsoft.com/en-us/services/bot-service/) without writing any code. Test your bot in the [Azure portal](https://portal.azure.com) or download and continue development.
5155

52-
## Quality search provided in a layered approach
56+
## Search quality and ranking provides the best possible answer
5357

54-
QnA Maker provides a layered approach
58+
QnA Maker provides a layered approach of Azure Search and QnA Maker. Queries are first sent to Azure Search, then the returned results are re-ranked by QnA Maker with information criteria such as metadata and multi-turn context.
5559

5660
## QnA Maker improves the conversation process
5761

@@ -79,8 +83,17 @@ QnA Maker provides authoring, training, and publishing along with collaboration
7983

8084
Learn what's new with QnA Maker.
8185

82-
* May 2019:
83-
* Multi-turn conversations
86+
* June 2019
87+
* Improved ranker model for French, Italian, German, Spanish, Portuguese
88+
* April 2019
89+
* Support website content extraction
90+
* Sharepoint document support
91+
* March 2019
92+
* Active learning
93+
* Improved NLP ranker model for English,
94+
95+
e. Jun: improved ranker model for French, Italian, German, Spanish, Portuguese
96+
8497

8598
## Next steps
8699
QnA Maker provides everything you need to build, manage and deploy your custom knowledge base.

0 commit comments

Comments
 (0)