Hi Rasa community!
we just published the final part of our three-piece blog post series in which share our best practices and recommendations how to custom-tailor the Rasa NLU pipeline for your individual contextual AI assistant.
This part is about hyperparameter tuning
- How to run a hyperparameter search at scale with Docker
- Which hyperparameters should I start with?
Read it here: Rasa NLU in Depth: Hyperparameter Tuning.
Also check out the other parts of this series:
- Part 1: Intent Recognition: Choose the right classifier for your AI assistant project
- Part 2: Entity Extraction – Choose the right extractor for each entity * Part 3: Hyperparameters – How to select and optimize them
Lets us know what your experiences and recommendations are for the perfect configuration of the NLU components