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

Peng Xu, Mostofa Patwary, Mohammad Shoeybi, Raul Puri, Pascale Fung, Anima Anandkumar, Bryan Catanzaro

Language Generation Long Paper

Gather-2I: Nov 17, Gather-2I: Nov 17 (10:00-12:00 UTC) [Join Gather Meeting]

You can open the pre-recorded video in a separate window.

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%).
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.

Connected Papers in EMNLP2020

Similar Papers

Grounded Compositional Outputs for Adaptive Language Modeling
Nikolaos Pappas, Phoebe Mulcaire, Noah A. Smith,
KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation
Wenhu Chen, Yu Su, Xifeng Yan, William Yang Wang,
PathQG: Neural Question Generation from Facts
Siyuan Wang, Zhongyu Wei, Zhihao Fan, Zengfeng Huang, Weijian Sun, Qi Zhang, Xuanjing Huang,