Merge pull request #97003 from diberry/diberry/1122-hack-alicia

[Cogsvcs] Hack - LUIS - What is - Alicia

Author: ktoliver

articles/cognitive-services/LUIS/what-is-luis.md

@@ -8,33 +8,62 @@ manager: nitinme
 ms.service: cognitive-services
 ms.subservice: language-understanding
 ms.topic: overview
-ms.date: 11/04/2019
+ms.date: 11/22/2019
 ms.author: diberry
 #Customer intent: As a developer incorporating LUIS into my client application, I want to understand what natural language processing (LUIS) is, so that I can determine if it will meet my Cognitive Language needs.
 ---
 
 # What is Language Understanding (LUIS)?
 
-Language Understanding (LUIS) is a cloud-based API service that applies custom machine-learning intelligence to a user's conversational, natural language text to predict overall meaning, and pull out relevant, detailed information. 
+Language Understanding (LUIS) is a cloud-based API service that applies custom machine-learning intelligence to natural language text to predict overall meaning, and pull out relevant, detailed information. 
 
-A client application for LUIS is any conversational application that communicates with a user in natural language to complete a task. Examples of client applications include social media apps, chat bots, and speech-enabled desktop applications.  
+For example, when a client application sends the text, `find me a wireless keyboard for $30`, LUIS responds with the following JSON object. 
+
+```JSON
+{
+    "query": "find me a wireless keyboard for $30",
+    "prediction": {
+        "topIntent": "Finditem",
+        "intents": {
+            "Finditem": {
+                "score": 0.934672
+            }
+        },
+        "entities": {
+            "item": [
+                "wireless keyboard"
+            ],
+            "money": [
+        {
+            "number": 30,
+            "units": "Dollar"
+        }
+           ]
+        }
+        
+    }
+}
+```
+In the example above, the _**intent**_, or overall meaning of the phrase is that the user is trying to find an item. The detailed pieces of information that LUIS extracts are called _**entities**_. In this case, the entities are the name of the item the user is looking for and the amount of money they want to spend.
+
+Client applications use LUIS's returned JSON, the _intent_ (category), and _entities_ (extracted detailed information), to drive actions in the client application. A client application for LUIS is often a conversational application that communicates with a user in natural language to complete a task. Examples of client applications include social media apps, chat bots, and speech-enabled desktop applications. 
 
 ![Conceptual image of 3 client applications working with Cognitive Services Language Understanding (LUIS)](./media/luis-overview/luis-entry-point.png "Conceptual image of 3 client applications working with Cognitive Services Language Understanding (LUIS)")
 
-## Use LUIS in a chat bot
+## Example use LUIS in a chat bot
 
 <a name="Accessing-LUIS"></a>
 
-Once the LUIS app is published, a client application sends utterances (text) to the LUIS natural language processing endpoint [API][endpoint-apis] and receives the results as JSON responses. A common client application for LUIS is a chat bot.
+A client application sends utterances (text) to the published LUIS natural language processing endpoint [API][endpoint-apis] and receives the results as JSON responses. A common client application for LUIS is a chat bot.
 
 
 ![Conceptual imagery of LUIS working with Chat bot to predict user text with natural language understanding (NLP)](./media/luis-overview/LUIS-chat-bot-request-response.svg "Conceptual imagery of LUIS working with Chat bot to predict user text with natural language understanding (NLP")
 
 |Step|Action|
 |:--|:--|
 |1|The client application sends the user _utterance_ (text in their own words), "I want to call my HR rep." to the LUIS endpoint as an HTTP request.|
-|2|LUIS enables you to craft your custom language models to add intelligence to your application. Machine learned language models take the user's unstructured input text and returns a JSON-formatted response, with a top intent, `HRContact`. The minimum JSON endpoint response contains the query utterance, and the top scoring intent. It can also extract data such as the _Contact Type_ entity.|
-|3|The client application uses the JSON response to make decisions about how to fulfill the user's requests. These decisions can include decision tree in the bot framework code and calls to other services. |
+|2|LUIS applies machine learned language models to the user's unstructured input text and returns a JSON-formatted response, with a top intent, `HRContact`. The minimum JSON endpoint response contains the query utterance, and the top scoring intent. It can also extract data such as the _Contact Type_ entity.|
+|3|The client application uses the JSON response to make decisions about how to fulfill the user's requests. These decisions can include a decision tree in the bot and calls to other services. |
 
 The LUIS app provides intelligence so the client application can make smart choices. LUIS doesn't provide those choices. 
 
@@ -43,16 +72,16 @@ The LUIS app provides intelligence so the client application can make smart choi
 
 ## Natural language processing
 
-Your LUIS app contains a domain-specific natural language model. You can start the LUIS app with a prebuilt domain model, build your own model, or blend pieces of a prebuilt domain with your own custom information.
+Your LUIS app contains domain-specific natural language models, which work together. You can start the LUIS app with one or more prebuilt models, build your own model, or blend prebuilt models with your own custom information.
 
-* **Prebuilt model** LUIS has many prebuilt domain models including intents, utterances, and prebuilt entities. You can use the prebuilt entities without having to use the intents and utterances of the prebuilt model. [Prebuilt domain models](luis-how-to-use-prebuilt-domains.md) include the entire design for you and are a great way to start using LUIS quickly.
+* **Prebuilt model** LUIS has many prebuilt domains that include intent and entity models that work together to complete common usage scenarios. These domains include labeled utterances that can be inspected and edited, allowing you to customize them. [Prebuilt domain models](luis-how-to-use-prebuilt-domains.md) include the entire design for you and are a great way to start using LUIS quickly. In addition, there are prebuilt entities such as currency and number that you can use independently from the prebuilt domains.
 
-* **Custom model** LUIS gives you several ways to identify your own custom models including intents, and entities. Entities include machine-learned entities, specific or literal entities, and a combination of machine-learned and literal.
+* **Custom model** LUIS gives you several ways to build your own custom models including intents, and entities. Entities include machine-learned entities, pattern matching entities, and a combination of machine-learned and pattern matching.
 
-## Build the LUIS model
-Build the model with the [authoring](https://go.microsoft.com/fwlink/?linkid=2092087) APIs or with the [LUIS portal](https://www.luis.ai).
+## Build the LUIS app
+Build the app with the [authoring](https://go.microsoft.com/fwlink/?linkid=2092087) APIs or with the [LUIS portal](https://www.luis.ai).
 
-The LUIS model begins with categories of user intentions called **[intents](luis-concept-intent.md)**. Each intent needs examples of user **[utterances](luis-concept-utterance.md)**. Each utterance can provide data that needs to be extracted. 
+The LUIS app begins with categories of input text called **[intents](luis-concept-intent.md)**. Each intent needs examples of user **[utterances](luis-concept-utterance.md)**. Each utterance can provide data that needs to be extracted. 
 
 |Example user utterance|Intent|Extracted data|
 |-----------|-----------|-----------|
@@ -96,8 +125,8 @@ After your LUIS app is published and receives real user utterances, LUIS provide
 
 <a name="using-luis"></a>
 
-## Development lifecycle
-LUIS provides tools, versioning, and collaboration with other LUIS authors to integrate into the full [development life cycle](luis-concept-app-iteration.md). 
+## Iterative development lifecycle
+LUIS provides tools, versioning, and collaboration with other LUIS authors to integrate into the full iterative [development life cycle](luis-concept-app-iteration.md). 
 
 ## Implementing LUIS
 Language Understanding (LUIS), as a REST API, can be used with any product, service, or framework with an HTTP request. The following list contains the top Microsoft products and services used with LUIS.
@@ -124,7 +153,7 @@ Samples using LUIS:
 ## Next steps
 
 * [What's new](whats-new.md)
-* Author a new LUIS app with a [prebuilt](luis-get-started-create-app.md) or [custom](luis-quickstart-intents-only.md) domain.
+* Author a new LUIS app with a [prebuilt](luis-get-started-create-app.md) or [custom](luis-quickstart-intents-only.md) domain
 * [Query the prediction endpoint](luis-get-started-get-intent-from-browser.md) of a public IoT app. 
 * [Developer resources](developer-reference-resource.md) for LUIS.