We use a few cookies

Essential cookies keep the library working. With your permission, we'd also like to use analytics to see what's useful and improve the experience. Read our Privacy Policy or Cookie Policy.

Skip to main content
Home/e-Resources/Artificial Intelligence & Machine Learning/A Plug-and-Play Method for Controlled Text Generation
Conference ProceedingsArtificial Intelligence & Machine Learning

A Plug-and-Play Method for Controlled Text Generation

2021

Checking your access to this record.

Abstract & Overview

Large pre-trained language models have repeatedly shown their ability to produce fluent text.Yet even when starting from a prompt, generation can continue in many plausible directions.Current decoding methods with the goal of controlling generation, e.g., to ensure specific words are included, either require additional models or fine-tuning, or work poorly when the task at hand is semantically unconstrained, e.g., story generation.In this work, we present a plug-and-play decoding method for controlled language generation that is so simple and intuitive, it can be described in a single sentence: given a topic or keyword, we add a shift to the probability distribution over our vocabulary towards semantically similar words.We show how annealing this distribution can be used to impose hard constraints on language generation, something no other plug-and-play method is currently able to do with SOTA language generators.Despite the simplicity of this approach, we see it works incredibly well in practice: decoding from GPT-2 leads to diverse and fluent sentences while guaranteeing the appearance of given guide words.We perform two user studies, revealing that (1) our method outperforms competing methods in human evaluations; and(2) forcing the guide words to appear in the generated text has no impact on the fluency of the generated text. 1

Cite this record

Damián Pascual, Béni Egressy, Clara Meister, Ryan Cotterell, Roger P. Wattenhofer (2021). A Plug-and-Play Method for Controlled Text Generation. https://doi.org/10.18653/v1/2021.findings-emnlp.334

Copy in another style

Pascual, D., Egressy, B., Meister, C., Cotterell, R., & Wattenhofer, R. P. (2021). A Plug-and-Play Method for Controlled Text Generation. https://doi.org/10.18653/v1/2021.findings-emnlp.334
Author names are used as deposited, so check their order before you submit.

Metadata is harvested from open-access indexes and can be incomplete. Check a citation against the published version before relying on it — see our open access & attribution policy.