PPLM builds on top of other large transformer-based generative models (like GPT-2), where it enables finer-grained control of attributes of the generated language (e.g. gradually switching topic 🐱 or sentiment 😃).
This controlled language generation method consists of plugging in simple bag-of-words or one-layer classifiers as attribute controllers, and making updates in the activation space, without changing any model parameters.
Kindly implemented by the Uber AI team in
From the paper Plug and Play Language Model: A simple baseline for controlled language generation by Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu.