These docs are for version 1.x of Rasa Open Source.

User Guide

• Installation
• Tutorial: Rasa Basics
• Tutorial: Building Assistants
• Command Line Interface
• Architecture
• Messaging and Voice Channels
• Evaluating Models
• Validate Data
• Configuring the HTTP API
• Deploying your Rasa Assistant
• Cloud Storage

NLU

• About
• Using NLU Only
• Training Data Format
• Choosing a Pipeline
• Language Support
• Entity Extraction
• Components

Core

• About
• Stories
• Domains
• Responses
• Actions
• Reminders and External Events
• Policies
• Slots
• Forms
• Retrieval Actions
• Interactive Learning
• Fallback Actions
• Knowledge Base Actions

Conversation Design

• Dialogue Elements
• Small Talk
• Completing Tasks
• Guiding Users

API Reference

• Action Server
• HTTP API
• Jupyter Notebooks
• Agent
• Custom NLU Components
• Rasa SDK
• Events
• Tracker
• Tracker Stores
• Event Brokers
• Lock Stores
• Training Data Importers
• Featurization of Conversations
• TensorFlow Configuration
• Migration Guide
• Rasa Open Source Change Log

Migrate from (beta)

• Dialogflow
• Wit.ai
• LUIS
• IBM Watson

Reference

• Glossary

Versions

viewing: 1.8.1

Featurization of Conversations

In order to apply machine learning algorithms to conversational AI, we need to build up vector representations of conversations.

Each story corresponds to a tracker which consists of the states of the conversation just before each action was taken.

State Featurizers

Every event in a trackers history creates a new state (e.g. running a bot action, receiving a user message, setting slots). Featurizing a single state of the tracker has a couple steps:

1. Tracker provides a bag of active features:

• features indicating intents and entities, if this is the first state in a turn (e.g. [intent_restaurant_search, entity_cuisine])

• features indicating which slots are currently defined (e.g. slot_location)

• features indicating the results of any API calls stored in slots (e.g. slot_matches)

• features indicating what the last action was (e.g. prev_action_listen)

2. Convert all the features into numeric vectors:

We use the X, y notation that’s common for supervised learning, where X is an array of shape (num_data_points, time_dimension, num_input_features), and y is an array of shape (num_data_points, num_bot_features) where the target class labels are encoded as one-hot vectors.

The target labels correspond to actions taken by the bot. There are different featurizers available:

• BinarySingleStateFeaturizer creates a binary one-hot encoding.
• LabelTokenizerSingleStateFeaturizer creates a vector based on the feature label.

Tracker Featurizers

It’s often useful to include a bit more history than just the current state when predicting an action. The TrackerFeaturizer iterates over tracker states and calls a SingleStateFeaturizer for each state. There are two different tracker featurizers:

1. Full Dialogue

FullDialogueTrackerFeaturizer creates numerical representation of stories. Therefore, X is an array of shape (num_stories, max_dialogue_length, num_input_features) and y is of shape (num_stories, max_dialogue_length, num_bot_features).

2. Max History

MaxHistoryTrackerFeaturizer creates an array of previous tracker states for each bot action with the parameter max_history defining how many states go into each row in X.