Improving Neural Story Generation by Targeted Common Sense Grounding
This addresses the issue of incoherent stories for users of AI-generated content, but it is incremental as it builds on existing methods with targeted improvements.
The paper tackled the problem of neural story generation lacking common sense reasoning by proposing a multi-task learning scheme with auxiliary training signals, achieving improved common sense reasoning and state-of-the-art perplexity on the Writing Prompts dataset.
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.