| 1 |
A Plug-and-Play Method for Controlled Text Generation ...
|
|
|
|
Abstract:
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: ... : Findings of the Association for Computational Linguistics: EMNLP 2021 ...
|
|
URL: http://hdl.handle.net/20.500.11850/518988
https://dx.doi.org/10.3929/ethz-b-000518988
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
