Hi @ganeshv. You should label each entity in your NLU examples for example:
Show me [chinese](cuisine), [mexican](cuisine) and [japansese](cuisine) restaurants.
To enable your assistant to extract these details as a list slot, define this slot in your domain, for example:
slots:
cuisine:
type: list
Then, when predicting on unseen inputs, for example I would like to get the list of chinese, mexican and japanese restaurants the model will extract all identified cuisine entities as a list [chinese, mexican, japanese].
Hi @Juste. So let’s say that I got my list of cuisines. Now if I want the user to confirm, something like: “Would you like to see a list of chinese, mexican and japanese restaurants?”. How can I fill a response with a list?