Hi there, My pipeline is below, and I am getting very low recognition of intents even when my reply is exactly the same as in nlu examples. Even when I type ‘yes’ the affirm intent has 0.54 instead of 1.00. Can someone tell me how to solve this? - name: SpacyNLP model: "en_core_web_md" - name: SpacyTokenizer - name: SpacyFeaturizer pooling: mean - name: SpacyEntityExtractor - name: CRFEntityExtractor - name: LexicalSyntacticFeaturizer - name: CountVectorsFeaturizer - name: CountVectorsFeaturizer - name: "SklearnIntentClassifier" C: [1, 5, 10, 50, 100] - name: EntitySynonymMapper

Intent recognition extremely low how to improve?

ChrisRahme (Chris Rahmé) February 8, 2022, 5:40pm 4

I highly suggest using Tensorboard (see this post to learn more).

Any reason you’re using this particular pipeline? Why not use DIET?

Topic		Replies	Views
Rasa with spaCy Rasa Open Source	3	475	March 3, 2022
NLU detects random input with wrong intent and high confidence Rasa Open Source	39	4909	July 27, 2022
Failing at intent classification Rasa Open Source	4	703	August 5, 2019
Intent classification poor even with exact matches Rasa Open Source	9	1071	June 5, 2020
As number of intents increases, confidence level decreases Rasa Open Source	7	1990	August 24, 2018