Advanced NLU v/s Standard NLU

[saurav_nair]

Can someone help me understand when should we use Advanced NLU in Dialogflow CX?

From my understanding, standard NLU is suitable during development as it has the auto-train ability and once we deploy the agent to Prod (let's assume its a different agent and not an environment), we can enable Advanced NLU as we don't expect any changes directly made to the prod agent. 

But if we do this can we guarantee that the testing done for the dev agent with standard NLU is sufficient and there won't be any unwanted behavior?

1. Is Advanced NLU recommended for all the agents built in Dialogflow CX or is there a specific criterion for choosing the NLU option?
2. What are actual ML algorithms used to train in Standard v/s Advanced NLU configuration? 

[cristianrm]

As shown in the Dialogflow CX - Agents documentation, in the NLU type section:

NLU type

This can be one of:

Standard

Standard NLU technology.

Advanced

Advanced NLU technology. This NLU type works better than standard, especially for large agents and flows. Model training takes longer, so automatic training is disabled. You need to train the flows manually or via API.

Therefore, the NLU advanced is recommended for large agents and flows. Note that the training model takes longer, so automatic training is disabled, and should be done through manual flows or using the API.

This article discusses further about Dialogflow CX.