Shipping Applied Research to Solve Real Problems

We are still in the early days of AI assistants and many things still need to be invented. Our research is driven by real challenges and datasets, and our primary aim is to help the Rasa community build better AI assistants.

Join us at Rasa Developer Summit to learn about the latest applied conversational AI research.

These are just some of the topics we're working on. The very curious can directly look at our active branches on GitHub.

Tranfer Learning Across Dialogue Tasks

You've built an assistant and it can already help users with a few things. Now you're adding new functionality. How can your assistant re-use the dialogue elements it already knows about in this new context?

Supervised Word Embeddings

Pre-trained word embeddings like word2vec and GloVe are a great way to build a simple text classifier. But learning supervised embeddings for your specific task helps you deal with jargon and out-of-vocabulary words. This is now our default intent classification model.

Entity Resolution using Knowledge Bases

Combining a dialogue system with a knowledge base allows developers to encode domain knowledge in a scalable way and integrate it with statistical NLU and dialogue models. It also helps your assistant understand messages like the second one or which of those is cheaper? .

Conversational Embeddings

Most language models and word embeddings are trained on prose and don't know anything about the rules of conversation. How can we build embeddings that understand the difference between purposeful dialogue and chit-chat, and can detect non-sequiturs?

Compressing Transformer Language Models

Large-scale language models like BERT, GPT-2, and XLNet show excellent performance on a number of NLU tasks but are very resource intensive. Can we compress these models to get something that's almost as accurate but much faster?

Talks and Meetups

We regularly host external speakers at our #botsBerlin meetup to talk about their research.

Academic Collaborations

We believe in open collaborations and work closely with a small number of research groups.


Our open source tools are used in research projects and papers at a growing number of leading institutions. In addition, TU Munich published a study benchmarking our NLU system.


We're a partner of the UKRI Centre for Doctoral Training in Natural Language Processing at the University of Edinburgh. We are also sponsors of SigDIAL 2019.


Every year we supervise a few MSc students and take on some interns to work on research. If you are using Rasa in a course, get in touch and we can share materials for use in lectures and group projects.