On-the-Fly Controlled Text Generation with Experts and Anti-Experts

05/07/2021 ∙ by Alisa Liu, et al. ∙ 0

Despite recent advances in natural language generation, it remains challenging to control attributes of generated text. We propose DExperts: Decoding-time Experts, a decoding-time method for controlled text generation which combines a pretrained language model with experts and/or anti-experts in an ensemble of language models. Intuitively, under our ensemble, output tokens only get high probability if they are considered likely by the experts, and unlikely by the anti-experts. We apply DExperts to language detoxification and sentiment-controlled generation, where we outperform existing controllable generation methods on both automatic and human evaluations. Our work highlights the promise of using LMs trained on text with (un)desired attributes for efficient decoding-time controlled language generation.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 7

page 14

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.