Training Conversations

To create a conversational chatbot that is able to complete specific tasks using the full context of a conversation, you must train your chatbot on a dataset of example conversations. These training conversations are a sequence of dialogue turns where each turn is annotated with additional pieces of information like the intent, tags, action type, and available slots. The specific annotations for each turn depend on whether it is a user turn or an agent turn.

Below is a very basic example of a training conversation. It teaches the bot to ask the user's name and then greet the user name.

User Turns

UTTERANCE: My name is David.

Assistant Turns

UTTERANCE: Hi, I'm a Bavard chatbot.
UTTERANCE: What is your name?
UTTERANCE: Nice to meet you, {{ PERSON }}.

In the last turn, you'll notice that the chatbot utterance uses a template where text {{ PERSON }} will be replaced with the value of the PERSON slot.