Sequentially Controlled Text Generation
Not on the map. Why?
Abstract (arXiv)
While GPT-2 generates sentences that are remarkably human-like, longer documents can ramble and do not follow human-like writing structure. We study the problem of imposing structure on long-range text. We propose a novel controlled text generation task, sequentially controlled text generation, and identify a dataset, NewsDiscourse as a starting point for this task. We develop a sequential controlled text generation pipeline with generation and editing. We test different degrees of structural awareness and show that, in general, more structural awareness results in higher control-accuracy, grammaticality, coherency and topicality, approaching human-level writing performance.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 46 of its 85 references that are in the map. First posted on arXiv 5 Jan 2023.
Builds on
46 of 85 references.
References · 46
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2020Longformer: The Long-Document Transformercited by 3,362
- 2019The Curious Case of Neural Text Degenerationcited by 2,881
- 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
- 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
- 2018Hierarchical Neural Story Generationcited by 1,182
- 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
- 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
- 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
- 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
- 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
34 more
- 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
- 2017Toward Controlled Generation of Textcited by 271
- 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 232
- 2017Challenges in Data-to-Document Generationcited by 226
- 2017Style Transfer in Text: Exploration and Evaluationcited by 145
- 2020Factual Error Correction for Abstractive Summarization Modelscited by 108
- 2020Explaining NLP Models via Minimal Contrastive Editing (MiCE)cited by 105
- 2020PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Trackingcited by 104
- 2019Encode, Tag, Realize: High-Precision Text Editingcited by 99
- 2020Content Planning for Neural Story Generation with Aristotelian Rescoringcited by 92
- 2019Do Massively Pretrained Language Models Make Better Storytellers?cited by 90
- 2017Generating Sentences by Editing Prototypescited by 88
- 2019Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modelingcited by 71
- 2019EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editingcited by 63
- 2018Learning Neural Templates for Text Generationcited by 61
- 2018Polite Dialogue Generation Without Parallel Datacited by 57
- 2020Neural Syntactic Preordering for Controlled Paraphrase Generationcited by 56
- 2018A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generationcited by 42
- 2022Controllable Text Generation with Neurally-Decomposed Oraclecited by 41
- 2020PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generationcited by 35
- 2018Simple Fusion: Return of the Language Modelcited by 30
- 2018Discourse-Aware Neural Rewards for Coherent Text Generationcited by 28
- 2022Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Featurescited by 24
- 2015Better Document-level Sentiment Analysis from RST Discourse Parsingcited by 20
- 2022Go Back in Time: Generating Flashbacks in Stories with Event Temporal Promptscited by 15
- 2021DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformercited by 14
- 2021Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learningcited by 14
- 2021Inference Time Style Control for Summarizationcited by 13
- 2021Guiding Neural Story Generation with Reader Modelscited by 12
- 2020Data-to-Text Generation with Iterative Text Editingcited by 11
- 2022Controllable Text Generation for Open-Domain Creativity and Fairnesscited by 6
- 2021"Don't quote me on that": Finding Mixtures of Sources in News Articlescited by 5
- 2019Attributed Rhetorical Structure Grammar for Domain Text Summarizationcited by 3
- 2020ETC-NLG: End-to-end Topic-Conditioned Natural Language Generationcited by 3
Built on by
Citing papers per year: 2023: 3; 2024: 0; 2025: 2.
5 papers.
- 2023Stay on topic with Classifier-Free Guidancecited by 90
- 2023Identifying Informational Sources in News Articlescited by 5
- 2023STRONG -- Structure Controllable Legal Opinion Summary Generationcited by 3
- 2025The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativitycited by 0
- 2025TaleFrame: An Interactive Story Generation System with Fine-Grained Control and Large Language Modelscited by 0
- 2025TaleFrame: An Interactive Story Generation System with Fine-Grained Control and Large Language Models2 Dec 2025
- 2025The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity3 Nov 2025
- 2023STRONG -- Structure Controllable Legal Opinion Summary Generation29 Sep 2023
- 2023Stay on topic with Classifier-Free Guidance30 Jun 2023
- 2023Identifying Informational Sources in News Articles24 May 2023