Let's say I'm building a medical assistance chatbot.

How do I validate that my model is working well or better than others.

Is there any standard validation metrics for it ?


It is impossible to answer this question because you have not defined what precisely you want your chatbot to do (and not to do!). Once you have defined that, you have your metric.

So the answer to your second question is: no, there is no standard validation metric.

|improve this answer|||||

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.