Why Rasa uses Sparse Layers in Transformers
By Johannes Mosig and Vladimir Vlasov. Feed forward neural network layers are typically fully connected, or dense. But do we actually need to connect every input…
Exploring Semantic Map Embeddings / Part II
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.…
Exploring Semantic Map Embeddings / Part I
We explore a new sparse text embedding that has some interesting properties.…
Custom Gensim Embeddings in Rasa
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 a…
Visualise Word-Embeddings with Whatlies
We're happy to announce that we're open sourcing a visualisation tool!…
Rasa NLU in Depth: Part 3 – Hyperparameter Tuning
Part 3 of our Rasa NLU in Depth series covers hyperparameter tuning. We will explain how to use Docker containers to run a Rasa NLU hyperparameter search for the best NLU pipeline at scale.…
Rasa NLU in Depth: Part 1 – Intent Classification
This is part one of our three-part in-depth series about Rasa NLU. It will cover intent classification components, when to choose which and how to solve common real-world problems.…