Intuitions on implementing ES on text data for text classification use-cases

[goodrahstar]

Hi, I would like to implement ES on text data can you please provide some intuitions on implementing ES for text classification use-cases.

Possibly should I injects noise directly in the parameter space (using Gaussian or other) i.e on embeddings or on raw text dataset.

Not sure if I am making any sense just trying to take a path which is not taken yet.

Regards, Rahul