mlsanityData to 7 Oct 2026

Improving Neural Story Generation by Targeted Common Sense Grounding

arXiv 1908.09451 ↗First posted 26 Aug 2019cs.LG cs.CL stat.MLcited by 16

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 4; 2023: 3.

16 papers.

Sort:

By area:

  1. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  2. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 256
  3. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  4. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  5. 2021The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generationcited by 96
  6. 2021Transformer-based Conditional Variational Autoencoder for Controllable Story Generationcited by 44
  7. 2021Automatic Story Generation: Challenges and Attemptscited by 28
  8. 2021Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanationscited by 24
  9. 2022Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generationcited by 15
  10. 2023GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidencecited by 14
  11. 2021On-the-Fly Attention Modulation for Neural Generationcited by 12
  12. 2021Sketch and Customize: A Counterfactual Story Generatorcited by 9
4 more
  1. 2021Outline to Story: Fine-grained Controllable Story Generation from Cascaded Eventscited by 8
  2. 2021TopNet: Learning from Neural Topic Model to Generate Long Storiescited by 2
  3. 2022An Ion Exchange Mechanism Inspired Story Ending Generator for Different Characterscited by 1
  4. 2023CASE: Commonsense-Augmented Score with an Expanded Answer Spacecited by 0