Hi Rasa community!
in a three-piece blog post series we want to share our best practices and recommendations how to custom-tailor the Rasa NLU pipeline for your individual contextual AI assistant.
We start the series with a blog post about intent classification, which gives you guidelines on
- which intent classification component you should use for your project
- how to tackle common problems: lack of training data, out-of-vocabulary words, robust classification of similar intents, and skewed datasets
Read it here: Rasa NLU in Depth: Intent Classification
In the next weeks we will publish the other two parts, namely
- 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 intent recognition with Rasa NLU