Consume LUIS outcome programmatically

In my last post, I explained how we can create a simple LUIS app and how the app can be trained and tested using various utterances.

Now, when the result from LUIS has to be used further, programmatically using C#, we do so in the following manner.

It’s a JSON outcome from LUIS. We create a console app which will reach out to the HTTP endpoint and get the JSON outcome that shall later be parsed to get the detail

Continue reading

Advertisements

Create a LUIS app

In my last post, I’ve explained what is LUIS and it’s various details. Here, we shall learn to create an app.

To be able to use a LUIS app, two major actions need to be accomplished

  • Create azure subscription keys
  • Create app in LUIS

We shall see each step one by one.

Continue reading

LUIS or Language Understanding Intelligent Service

As mentioned in my last post, LUIS is an API.

LUIS allows your application to understand what a person wants in their own words.

  • LUIS uses machine learning to allow developers to build applications
  • These applications can receive user input in natural language
  • LUIS extracts meaning from it the user input

A client application that converses with the user (ex- SharePoint search, or a chatbot) can pass user input to a LUIS app and receive relevant, detailed information back.

Continue reading

Natural Language Processing

Natural language processing (NLP) is the ability of a computer program to understand human language as it is spoken. NLP is a component of artificial intelligence.

Why is NLP development challenging?
The development of NLP applications is challenging because computers conventionally require humans to “speak” to them in a programming language that is precise, unambiguous and highly structured, or through a limited number of clearly articulated voice commands. Human speech, however, is not always precise — it is often ambiguous and the linguistic structure can depend on many complex variables, including slang, regional dialects and social context.

Continue reading