Just like there is run_evaluation for evaluating predicted Intents, is there anything similar to evaluate entities extracted?
akelad
(Akela Drissner)
2
Yep that evaluation script evaluates both entities and intents
I see using run_evaluation results are different in Jupyter notebook and on command line:
On command line: I can see confusion matrix for entities:
But in Jupyter notebook: confusion matrix is not shown:
The version of the notebook server is: 5.5.0
Python 3.6.5 |Anaconda custom (64-bit)| (default, Mar 29 2018, 13:32:41)
rasa_nlu: 0.13.4
Am I missing anything?
See this, it helps resolve issue: