Hierarchical Neural Story Generation

Code

• github.com/pytorch/fairseq
  OfficialIn paperpytorch★ 32,198
• github.com/facebookresearch/fairseq
  pytorch★ 32,199
• github.com/yangkevin2/emnlp22-re3-story-generation
  pytorch★ 255
• github.com/Advancing-Machine-Human-Reasoning-Lab/apt
  pytorch★ 25
• github.com/AnirudhMukherjee/story-generation
  tf★ 0
• github.com/pumpkinman008/StoryGeneration
  tf★ 0
• github.com/Kickflip89/NLP_Project
  pytorch★ 0

Abstract

We explore story generation: creative systems that can build coherent and fluent passages of text about a topic. We collect a large dataset of 300K human-written stories paired with writing prompts from an online forum. Our dataset enables hierarchical story generation, where the model first generates a premise, and then transforms it into a passage of text. We gain further improvements with a novel form of model fusion that improves the relevance of the story to the prompt, and adding a new gated multi-scale self-attention mechanism to model long-range context. Experiments show large improvements over strong baselines on both automated and human evaluations. Human judges prefer stories generated by our approach to those from a strong non-hierarchical model by a factor of two to one.

Tasks

Reproductions