Improving Neural Story Generation by Targeted Common Sense Grounding
Machine Learning
2020-03-02 v2 Computation and Language
Machine Learning
Abstract
Stories generated with neural language models have shown promise in grammatical and stylistic consistency. However, the generated stories are still lacking in common sense reasoning, e.g., they often contain sentences deprived of world knowledge. We propose a simple multi-task learning scheme to achieve quantitatively better common sense reasoning in language models by leveraging auxiliary training signals from datasets designed to provide common sense grounding. When combined with our two-stage fine-tuning pipeline, our method achieves improved common sense reasoning and state-of-the-art perplexity on the Writing Prompts (Fan et al., 2018) story generation dataset.
Cite
@article{arxiv.1908.09451,
title = {Improving Neural Story Generation by Targeted Common Sense Grounding},
author = {Huanru Henry Mao and Bodhisattwa Prasad Majumder and Julian McAuley and Garrison W. Cottrell},
journal= {arXiv preprint arXiv:1908.09451},
year = {2020}
}