Neatly Packaged Manuals

    TypeScript icon, indicating that this package has built-in type declarations

    4.16.0 • Public • Published

    Language Generation

    Learning from our customers experiences and bringing together capabilities first implemented by Cortana and Cognition teams, we are introducing Language Generation; which allows the developer to extract the embedded strings from their code and resource files and manage them through a Language Generation runtime and file format. Language Generation enable customers to define multiple variations on a phrase, execute simple expressions based on context, refer to conversational memory, and over time will enable us to bring additional capabilities all leading to a more natural conversational experience.

    At the core of language generation lies template expansion and entity substitution. You can provide one-of variation for expansion as well as conditionally expand a template. The output from language generation can be a simple text string or multi-line response or a complex object payload that a layer above language generation will use to construct a full blown activity.

    Language generation is achieved through:

    • markdown based .lg file that describes the templates and their composition. See here for the .lg file format.
    • full access to current bots memory so you can data bind language to the state of memory.
    • parser and runtime libraries that help achieve runtime resolution. See here for API-reference.
    # greetingTemplate
    - Hello ${}, how are you?
    - Good morning ${}. It's nice to see you again.
    - Good day ${}. What can I do for you today?

    You can use language generation to:

    • achieve a coherent personality, tone of voice for your bot
    • separate business logic from presentation
    • include variations and sophisticated composition based resolution for any of your bot's replies
    • structured LG

    structured LG

    The type of LG output could be string or object, string is by default. But LG could generate a json object by Structured LG feature.

    Example here:

        # HeroCardTemplate(buttonsCollection)
        # TitleText
        - Here are some ${TitleSuffix()}
        # TitleSuffix
        - cool photos
        - pictures
        - nice snaps
        # SubText
        - What is your favorite?
        - Don't they all look great?
        - sorry, some of them are repeats
        # DescriptionText
        - This is description for the hero card
        # CardImages

    the result could be:

      "lgType": "Herocard",
      "title": "Here are some pictures",
      "text": "This is description for the hero card",
      "images": "",
      "buttons": [
        "click to see",

    the structured name would be placed into property 'lgType'. See more tests here : structured LG test

    By this, You can use the ActivityFactory.fromObject(lgResult) method to transform the lg output into a Bot Framework activity to post back to the user.

    see more samples here: Structured LG to Activity

    Language Generation in action

    When building a bot, you can use language generation in several different ways. To start with, examine your current bot's code (or the new bot you plan to write) and create .lg file to cover all possible scenarios where you would like to use the language generation sub-system with your bot's replies to user.

    Then make sure you include the platform specific language generation library.

    For C#, add Microsoft.Bot.Builder.LanguageGeneration. For NodeJS, add botbuilder-lg

    Load the template manager with your .lg file

        let templates = new Templates.parseFile(filePath, importResolver?, expressionParser?);

    When you need template expansion, call the templates and pass in the relevant template name

        await turnContext.sendActivity(templates.evaluate("<TemplateName>", entitiesCollection));

    If your template needs specific entity values to be passed for resolution/ expansion, you can pass them in on the call to evaluateTemplate

        await turnContext.sendActivity(templates.evaluate("WordGameReply", { GameName = "MarcoPolo" } ));

    Develop notice

    If you changed the g4 file, please use antlr-build-expression and antlr-build-commonregex to generate latest lexer/parser. By the way, You will need to have a modern version of Java (>= JRE 1.6) to use it.


    npm i botbuilder-lg

    DownloadsWeekly Downloads






    Unpacked Size

    1.21 MB

    Total Files


    Last publish


    • botframework
    • joshgummersall
    • sgellock
    • cwhitten