Conversational AI
For updates regarding how we utilize, improve upon, and explore conversational AI technologies, check out this category for related blog posts!
April 19th, 2021
Why Rasa uses Sparse Layers in Transformers
Johannes Mosig
Vladimir Vlasov
Feed forward neural network layers are typically fully connected, or _dense_. But do we actually need to connect every input with every output? And if not, which inputs should we connect to which outputs?
March 8th, 2021
Takeaways from Two Recent Rasa Production Stories
Karen White
Curious about our takeaways from recent Rasa Production Stories? We examine 5 key insights from enterprises adopting conversational AI.
March 4th, 2021
Exploring Semantic Map Embeddings / Part II
Rasa
Johannes Mosig
In this second part of our series on semantic maps, we show how to create them and see how they perform as featurizers for DIET.
February 24th, 2021
Exploring Semantic Map Embeddings / Part I
Johannes Mosig
Are you interested in semantic map embedding? We explore a new sparse text embedding that has some interesting properties.
January 5th, 2021
Getting Back on the Happy Path
Karen White
Check out our blog and learn how to guide users toward successful interactions with chatbots through conversation design.
December 3rd, 2020
Using Rasa Github Action for Custom Action Server Images
Justina Petraitytė
In this tutorial we would like to show you how you can use Rasa Github Action to automate your Rasa custom action development workflow.
November 9th, 2020
Rasa for Content Creators
Karen White
Content creators contribute one of the most visible parts of an assistant: the personality, responses, and conversation flows.
September 21st, 2020
Introducing Rasa for Beginners
Mady Mantha
We’re excited to launch Rasa for Beginners: a free, introductory, hands-on course that will help you build your first functional and interactive AI assistant.
September 4th, 2020
Custom Gensim Embeddings in Rasa
Vincent Warmerdam
Training your own word embeddings can be a hassle, and we typically advise against it. It can require a lot of computing power, time, and more.
September 3rd, 2020
The CDD Playbook: Strategies for Conversation-Driven Development
Karen White
Learn concrete, actionable steps for building AI assistants using conversation-driven development in this helpful post for enterprises.
September 2nd, 2020
Putting Conversation-Driven Development to the Test
Alan Nichol
What we learned testing two assistants side by side: one developed using conversation-driven development, the other attempting to break as many CDD “rules” as we could.
August 20th, 2020
Superhero Spotlight: Bhavani Ravi
Emma Jade Wightman
In this series we will shed light on the extraordinary community work done by our Rasa Superheroes, take a deep dive into what inspired them, and find out if they have any tips or advice to share with aspiring community builders. In this edition, we get to know Bhavani Ravi!
August 6th, 2020
Recipes for Building Conversational AI Teams
Karen White
We’ll break down a few of the most common roles that make up conversational AI teams and consider a few example team structures to help you assemble your AI assistant dev team.
July 10th, 2020
10 Best Practices for Designing NLU Training Data
Karen White
Whether you're starting from scratch or working with an existing data set, here's how to make sure your NLU training data results in accurate predictions and scales sustainably.
June 22nd, 2020
Demonstration of TED Policy in Rasa Dialogue Management
Vincent Warmerdam
This guide accompanies a video on our algorithm whiteboard playlist. You can see the video below, but we figured that having a written guide would make it easier for our community members to reproduce our experiment.