Version: Latest

Contextual Conversations

Taking context into account is often key to providing a good user experience. This page is a guide to creating contextual conversation patterns.

NLU-based assistants

This section refers to building NLU-based assistants. If you are working with Conversational AI with Language Models (CALM), this content may not apply to you.

In a contextual conversation, something beyond the previous step in the conversation plays a role in what should happen next. For example, if a user asks "How many?", it's not clear from the message alone what the user is asking about. In the context of the assistant saying, "You've got mail!", the response could be "You have five letters in your mailbox". In the context of a conversation about outstanding bills, the response could be, "You have three overdue bills". The assistant needs to know the previous action to choose the next action.

To create a context-aware conversational assistant, you need to define how the conversation history affects the next response.

For example, if a user asks the example concert bot how to get started, the bot responds differently based on whether or not they like music:

A conversation with a user who likes music:

User: How can I get started ?

Bot: I can help you find concerts and venues. Do you like music?

User: yes

Bot: Awesome! You can ask me things like "Find me some concerts" or "What's a good venue"

User likes music

A conversation with a user who doesn't like music:

User: How can I get started ?

Bot: I can help you find concerts and venues. Do you like music?

User: no

Bot: Oh no!

User doesn't like music

Step-by-step Guide on Creating Contextual Conversation Patterns

1. Defining Slots

Slots are your assistant's memory. Slots store pieces of information that your assistant needs to refer to later and can direct the flow of the conversation based on slot_was_set events. There are different types of slots, and each affects the conversation flow in its own way.

In the concert bot example, the likes_music slot is a boolean slot. If it is true, the bot sends an intro message. If it is false, the bot sends a different message. You define a slot and its type in the domain:

domain.yml
slots:
likes_music:
type: bool
mappings:
- type: custom

2. Creating Stories

Stories are examples of how conversations should go. In the example above, the concert bot responds differently for users who like music and users who don't because of these two stories:

stories.yml
stories:
- story: User likes music
steps:
- intent: how_to_get_started
- action: utter_get_started
- intent: affirm
- action: action_set_music_preference
- slot_was_set:
- likes_music: True
- action: utter_awesome
- story: User doesn't like music
steps:
- intent: how_to_get_started
- action: utter_get_started
- intent: deny
- action: action_set_music_preference
- slot_was_set:
- likes_music: False
- action: utter_goodbye

These stories diverge based on the user's intent (affirm or deny). Based on the user's intent, a custom action sets a slot that further directs the conversation.

3. Configuring the TEDPolicy

In addition to adding stories to account for context, machine learning policies can help your model generalize to unseen conversation paths. It is important to understand that using machine-learning policies does not mean letting go of control over your assistant. If a rule-based policy is able to make a prediction, that prediction will always have a higher policy priority and will predict the next action.

The TEDPolicy is made to handle unexpected user behaviors. For example, in the conversation below (extracted from a conversation on Rasa X/Enterprise):

stories:
- story: Story from conversation with a2baab6c83054bfaa8d598459c659d2a on November 28th 2019
steps:
- checkpoint: STORY_START
- intent: greet
- action: action_greet_user
- slot_was_set:
- shown_privacy: true
- intent: ask_whoisit
- action: action_chitchat
- intent: ask_whatspossible
- action: action_chitchat
- intent: telljoke
- action: action_chitchat
- intent: how_to_get_started
entities:
- product: enterprise
- slot_was_set:
- product: enterprise
- action: utter_explain_enterprise
- action: utter_also_explain_nlucore
- intent: affirm
- action: utter_explain_nlu
- action: utter_explain_core
- action: utter_direct_to_step2

Here we can see the user has completed a few chitchat tasks first, and then ultimately asks how they can get started with Rasa X/Enterprise. The TEDPolicy correctly predicts that Rasa X/Enterprise should be explained to the user, and then also takes them down the getting started path, without asking all the qualifying questions first.

Since the machine-learning policy has generalized to this situation, you should add this story to your training data to continuously improve your bot and help the model generalize better in future. Rasa X/Enterprise is a tool that can help you improve your bot and make it more contextual.

Setting max_history

Usually, only a certain amount of context is relevant to your assistant. max_history is a hyperparameter for Rasa dialogue management policies that controls how many steps in a dialogue the model looks at to decide which action to take next.

In the story below, the user asks for help three times in a row. The first two times, the bot sends the same message, but the third time, it hands them off to a human

stories.yml
stories:
- story: user persists in asking for help
steps:
- intent: help
- action: utter_help
- intent: help
- action: utter_help
- intent: help
- action: action_human_handoff

In order for the model to learn this pattern, it needs to know at least the previous four steps i.e. max_history of four. If max_history were 3, the model would not have enough context to see that the user had already sent two help requests, and would never predict the human handoff action.

You can set the max_history by passing it to your policy's settings in your config file, for example:

config.yml
policies:
- name: "TEDPolicy"
max_history: 5

You want to make sure max_history is set high enough to account for the most context your assistant will need to make an accurate prediction about what to do next. For more details see the docs on featurizers.

Summary

Here's a summary of the concepts you can apply to enable your assistant to have contextual conversations:

  • Write stories for contextual conversations
  • Use slots to store contextual information for later use
  • Set the max_history for your policies appropriately for the amount of context your bot needs
  • Use the TEDPolicy for generalization to unseen conversation paths