The Rasa Blog
For updates regarding how we utilize, improve upon, and explore conversational AI technologies, check out this category for related blog posts!
August 12th, 2020
Introducing Entity Roles and Groups
At a fundamental level, natural language understanding (NLU) does two things: it identifies the goal or meaning of the text and extracts…
August 6th, 2020
Recipes for Building Conversational AI Teams
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
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
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.
June 17th, 2020
5 Levels of Conversational AI: 2020 Update
Since we first published the 5 levels of AI assistants, the market and tech have changed, and it’s time for an update. End users are already telling us what they want from AI assistants, and to get to level 5 we “just” have to listen.
April 24th, 2020
New Rasa Starter Pack: IT Helpdesk
This assistant is a great starting point for building an IT helpdesk chatbot of your own, or you can use it as a reference implementation for integrating with a customer service ticketing system.
April 20th, 2020
Visualise Word-Embeddings with Whatlies
We're happy to announce that we're open sourcing a visualisation tool!
March 9th, 2020
Introducing DIET: state-of-the-art architecture that outperforms fine-tuning BERT and is 6X faster to train
With Rasa 1.8, our research team is releasing a new state-of-the-art lightweight, multitask transformer architecture for NLU: Dual Intent and Entity Transformer (DIET).
January 28th, 2020
Model Testing and CI for conversational Software
An AI assistant is a product, and just because that product uses machine learning doesn’t mean you should give up on good software engineering habits.
December 17th, 2019
Rasa Open Source + Rasa X: Better Together
We recently launched Rasa X, a free toolset that helps you quickly iterate on and improve the quality of your contextual assistant built using Rasa Open Source.
September 5th, 2019
Pruning BERT to accelerate inference
After previously discussing various ways of accelerating models like BERT, in this blog post we empirically evaluate the pruning approach.…
August 27th, 2019
How to build a voice assistant with open source Rasa and Mozilla tools
What if you wanted to build and assistant that runs locally and ensures the privacy of your data? You can do it using Rasa Open Source, Mozilla DeepSpeech and Mozilla TTS tools. Check out this tutorial to find out how.
August 15th, 2019
Customizing Training Data Importing
Since Rasa version 1.2 you can customize the way Rasa imports training data for the model training. This tutorial shows you how to use provided out-of-the-box components or how to build your own importer module and plug it into Rasa.
August 8th, 2019
Compressing BERT for faster prediction
Let's look at compression methods for neural networks, such as quantization and pruning. Then, we apply one to BERT using TensorFlow Lite.
June 26th, 2019
Building a Common Language for Conversational AI
We start creating a common language to talk about the structure of conversations with AI assistants.