Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published November 6, 2020 | Submitted
Report Open

MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models

Abstract

Existing pre-trained large language models have shown unparalleled generative capabilities. However, they are not controllable. In this paper, we propose MEGATRON-CNTRL, a novel framework that uses large-scale language models and adds control to text generation by incorporating an external knowledge base. Our framework consists of a keyword predictor, a knowledge retriever, a contextual knowledge ranker, and a conditional text generator. As we do not have access to ground-truth supervision for the knowledge ranker, we make use of weak supervision from sentence embedding. The empirical results show that our model generates more fluent, consistent, and coherent stories with less repetition and higher diversity compared to prior work on the ROC story dataset. We showcase the controllability of our model by replacing the keywords used to generate stories and re-running the generation process. Human evaluation results show that 77.5% of these stories are successfully controlled by the new keywords. Furthermore, by scaling our model from 124 million to 8.3 billion parameters we demonstrate that larger models improve both the quality of generation (from 74.5% to 93.0% for consistency) and controllability (from 77.5% to 91.5%).

Additional Information

This work was done during the internship of Peng Xu at NVIDIA.

Attached Files

Submitted - 2010.00840.pdf

Files

2010.00840.pdf
Files (710.1 kB)
Name Size Download all
md5:e01366b2c00e612b00f5dbfa5b2f1bf7
710.1 kB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 20, 2023