Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DOC: Improving Long Story Coherence With Detailed Outline Control (2212.10077v3)

Published 20 Dec 2022 in cs.CL and cs.AI

Abstract: We propose the Detailed Outline Control (DOC) framework for improving long-range plot coherence when automatically generating several-thousand-word-long stories. DOC consists of two complementary components: a detailed outliner and a detailed controller. The detailed outliner creates a more detailed, hierarchically structured outline, shifting creative burden from the main drafting procedure to the planning stage. The detailed controller ensures the more detailed outline is still respected during generation by controlling story passages to align with outline details. In human evaluations of automatically generated stories, DOC substantially outperforms a strong Re3 baseline (Yang et al., 2022) on plot coherence (22.5% absolute gain), outline relevance (28.2%), and interestingness (20.7%). Humans also judged DOC to be much more controllable in an interactive generation setting.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  2. Towards a model-theoretic view of narratives. In Proceedings of the Third Workshop on Narrative Understanding, pages 95–104.
  3. Talebrush: Sketching stories with generative pretrained language models. In CHI Conference on Human Factors in Computing Systems, pages 1–19.
  4. Wordcraft: a human-ai collaborative editor for story writing. arXiv preprint arXiv:2107.07430.
  5. Chiara Coetzee. 2023. Generating a full-length work of fiction with gpt-4.
  6. Plug and play language models: A simple approach to controlled text generation. arXiv preprint arXiv:1912.02164.
  7. Hierarchical neural story generation. arXiv preprint arXiv:1805.04833.
  8. Content planning for neural story generation with aristotelian rescoring. arXiv preprint arXiv:2009.09870.
  9. Plan, write, and revise: an interactive system for open-domain story generation. arXiv preprint arXiv:1904.02357.
  10. Longt5: Efficient text-to-text transformer for long sequences. arXiv preprint arXiv:2112.07916.
  11. Improved lexically constrained decoding for translation and monolingual rewriting. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 839–850.
  12. Creative writing with an ai-powered writing assistant: Perspectives from professional writers. arXiv preprint arXiv:2211.05030.
  13. Opt-iml: Scaling language model instruction meta learning through the lens of generalization. arXiv preprint arXiv:2212.12017.
  14. Large language models are zero-shot reasoners. arXiv preprint arXiv:2205.11916.
  15. Gedi: Generative discriminator guided sequence generation. arXiv preprint arXiv:2009.06367.
  16. Less annotating, more classifying–addressing the data scarcity issue of supervised machine learning with deep transfer learning and bert-nli.
  17. Coauthor: Designing a human-ai collaborative writing dataset for exploring language model capabilities. arXiv preprint arXiv:2201.06796.
  18. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
  19. Cut the carp: Fishing for zero-shot story evaluation. arXiv preprint arXiv:2110.03111.
  20. Document-level neural machine translation with hierarchical attention networks. arXiv preprint arXiv:1809.01576.
  21. Co-writing screenplays and theatre scripts with language models: An evaluation by industry professionals. arXiv preprint arXiv:2209.14958.
  22. Planning with learned entity prompts for abstractive summarization. Transactions of the Association for Computational Linguistics, 9:1475–1492.
  23. OpenAI. 2023. Gpt-4.
  24. Training language models to follow instructions with human feedback. arXiv preprint arXiv:2203.02155.
  25. Counterfactual story reasoning and generation. arXiv preprint arXiv:1909.04076.
  26. Plotmachines: Outline-conditioned generation with dynamic plot state tracking. arXiv preprint arXiv:2004.14967.
  27. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084.
  28. Multitask prompted training enables zero-shot task generalization. arXiv preprint arXiv:2110.08207.
  29. Yufei Tian and Nanyun Peng. 2022. Zero-shot sonnet generation with discourse-level planning and aesthetics features. In 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL).
  30. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  31. Language modeling via stochastic processes. arXiv preprint arXiv:2203.11370.
  32. Tianming Wang and Xiaojun Wan. 2019. T-cvae: Transformer-based conditioned variational autoencoder for story completion. In IJCAI, pages 5233–5239.
  33. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations, pages 38–45.
  34. Autoformalization with large language models. arXiv preprint arXiv:2205.12615.
  35. Megatron-cntrl: Controllable story generation with external knowledge using large-scale language models. arXiv preprint arXiv:2010.00840.
  36. Kevin Yang and Dan Klein. 2021. Fudge: Controlled text generation with future discriminators. arXiv preprint arXiv:2104.05218.
  37. Re3: Generating longer stories with recursive reprompting and revision. arXiv preprint arXiv:2210.06774.
  38. Hierarchical attention networks for document classification. In Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies, pages 1480–1489.
  39. Plan-and-write: Towards better automatic storytelling. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 7378–7385.
  40. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068.
  41. Bridging the structural gap between encoding and decoding for data-to-text generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2481–2491, Online. Association for Computational Linguistics.
  42. Alpa: Automating inter-and intra-operator parallelism for distributed deep learning. arXiv preprint arXiv:2201.12023.
  43. Adapting language models for zero-shot learning by meta-tuning on dataset and prompt collections. arXiv preprint arXiv:2104.04670.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets