Authors: Angela Fan , Mike Lewis , Yann N. Dauphin - Annual Meeting of the Association for Computational Linguistics, ACL 2018 cited by 1,124
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.
✨ Checking sign-in… PDF Cited by View BibTeX Hide BibTeX View BibTeX Cite
Sequence to Sequence Learning with Neural… Sequence to Sequence Learning with Neural Networks Diverse Beam Search: Decoding Diverse… Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models A Diversity-Promoting Objective Function for… A Diversity-Promoting Objective Function for Neural Conversation Models Layer Normalization Layer Normalization Exploring the Limits of Language Modeling Exploring the Limits of Language Modeling Convolutional Sequence to Sequence Learning Convolutional Sequence to Sequence Learning Generating High-Quality and Informative… Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models Language Modeling with Gated Convolutional… Language Modeling with Gated Convolutional Networks Unsupervised Pretraining for Sequence to Sequenc… Unsupervised Pretraining for Sequence to Sequence Learning Toward Automated Story Generation with Markov… Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks Cold Fusion: Training Seq2Seq Models Together… Cold Fusion: Training Seq2Seq Models Together with Language Models Generating Wikipedia by Summarizing Long… Generating Wikipedia by Summarizing Long Sequences Don't Give Me the Details, Just the… Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization Document Expansion by Query Prediction Document Expansion by Query Prediction Plug and Play Language Models: A Simple… Plug and Play Language Models: A Simple Approach to Controlled Text Generation Narrative Interpolation for Generating and… Narrative Interpolation for Generating and Understanding Stories Rigid Formats Controlled Text Generation Rigid Formats Controlled Text Generation Generating similes effortlessly like a Pro… Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation Recursively Summarizing Books with Human… Recursively Summarizing Books with Human Feedback Open-world Story Generation with… Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey Aligning Language Models with Preferences throug… Aligning Language Models with Preferences through f-divergence Minimization Intrinsic Dimension Estimation for Robust… Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts A Survey on Hallucination in Large… A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions RLAIF vs. RLHF: Scaling Reinforcement Learning… RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback Hierarchical Neural Story Generation Hierarchical Neural Story Generation Earlier references Focus paper Citing papers Older Newer Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.
