mlsanityData to 14 Oct 2026

Plan-then-Generate: Controlled Data-to-Text Generation via Planning

arXiv 2108.13740 ↗First posted 31 Aug 2021cs.CLcited by 52

Not on the map. Why?

Abstract (arXiv)

Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In this study, we propose a novel Plan-then-Generate (PlanGen) framework to improve the controllability of neural data-to-text models. Extensive experiments and analyses are conducted on two benchmark datasets, ToTTo and WebNLG. The results show that our model is able to control both the intra-sentence and inter-sentence structure of the generated output. Furthermore, empirical comparisons against previous state-of-the-art methods show that our model improves the generation quality as well as the output diversity as judged by human and automatic evaluations.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Builds on 31 of its 55 references that are in the map. First posted on arXiv 31 Aug 2021.

Builds on

31 of 55 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  7. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  8. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  9. 2018Hierarchical Neural Story Generationcited by 1,193
  10. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 491
  11. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 268
  12. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 253
19 more
  1. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  2. 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
  3. 2020Open Question Answering over Tables and Textcited by 163
  4. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
  5. 2020Investigating Pretrained Language Models for Graph-to-Text Generationcited by 117
  6. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
  7. 2020Text-to-Text Pre-Training for Data-to-Text Taskscited by 104
  8. 2019Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generationcited by 75
  9. 2018Learning Neural Templates for Text Generationcited by 61
  10. 2017Table-to-text Generation by Structure-aware Seq2seq Learningcited by 54
  11. 2019Few-Shot NLG with Pre-Trained Language Modelcited by 52
  12. 2019Neural data-to-text generation: A comparison between pipeline and end-to-end architecturescited by 51
  13. 2019Data-to-text Generation with Entity Modelingcited by 45
  14. 2021Non-Autoregressive Text Generation with Pre-trained Language Modelscited by 36
  15. 2021Few-Shot Table-to-Text Generation with Prototype Memorycited by 21
  16. 2018End-to-End Content and Plan Selection for Data-to-Text Generationcited by 20
  17. 2019Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generationcited by 20
  18. 2020Variational Template Machine for Data-to-Text Generationcited by 19
  19. 2016Multi-domain Neural Network Language Generation for Spoken Dialogue Systemscited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 18; 2023: 19; 2024: 9; 2025: 2; 2026: 1.

52 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  2. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  3. 2022A Contrastive Framework for Neural Text Generationcited by 225
  4. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 202
  5. 2022Chart-to-Text: A Large-Scale Benchmark for Chart Summarizationcited by 169
  6. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  7. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 129
  8. 2022Language Models Can See: Plugging Visual Controls in Text Generationcited by 90
  9. 2022Automatic Generation of Socratic Subquestions for Teaching Math Word Problemscited by 43
  10. 2023ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoningcited by 42
  11. 2021TaCL: Improving BERT Pre-training with Token-aware Contrastive Learningcited by 32
  12. 2022Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learningcited by 32
38 more
  1. 2021Control Prefixes for Parameter-Efficient Text Generationcited by 24
  2. 2022Neural Pipeline for Zero-Shot Data-to-Text Generationcited by 19
  3. 2022GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generationcited by 16
  4. 2022MVP: Multi-task Supervised Pre-training for Natural Language Generationcited by 16
  5. 2023Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarizationcited by 14
  6. 2023Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialoguecited by 14
  7. 2024Unifying Structured Data as Graph for Data-to-Text Pre-Trainingcited by 13
  8. 2023Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domaincited by 11
  9. 2023LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Controlcited by 8
  10. 2022MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generationcited by 7
  11. 2023Toward Unified Controllable Text Generation via Regular Expression Instructioncited by 7
  12. 2022Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Frameworkcited by 6
  13. 2023Improving User Controlled Table-To-Text Generation Robustnesscited by 6
  14. 2023PixT3: Pixel-based Table-To-Text Generationcited by 6
  15. 2024A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generationcited by 6
  16. 2024Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialoguecited by 6
  17. 2022Plug-and-Play Recipe Generation with Content Planningcited by 5
  18. 2023Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Controlcited by 5
  19. 2023Generating Faithful Text From a Knowledge Graph with Noisy Reference Textcited by 4
  20. 2022Few-Shot Table-to-Text Generation with Prefix-Controlled Generatorcited by 3
  21. 2023ReTAG: Reasoning Aware Table to Analytic Text Generationcited by 3
  22. 2024Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTocited by 3
  23. 2022Lexical Complexity Controlled Sentence Generationcited by 2
  24. 2023Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorizationcited by 2
  25. 2023Plan-then-Seam: Towards Efficient Table-to-Text Generationcited by 2
  26. 2023Adapting Knowledge for Few-shot Table-to-Text Generationcited by 2
  27. 2023Controlling keywords and their positions in text generationcited by 2
  28. 2023You Can Generate It Again: Data-to-Text Generation with Verification and Correction Promptingcited by 2
  29. 2023Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selectioncited by 2
  30. 2023Automatic Logical Forms improve fidelity in Table-to-Text generationcited by 2
  31. 2024Satyrn: A Platform for Analytics Augmented Generationcited by 2
  32. 2023Compositional Generalization for Data-to-Text Generationcited by 1
  33. 2024Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigationcited by 1
  34. 2025Alternatives To Next Token Prediction In Text Generation -- A Surveycited by 1
  35. 2022High Recall Data-to-text Generation with Progressive Editcited by 0
  36. 2024Inroads to a Structured Data Natural Language Bijection and the role of LLM annotationcited by 0
  37. 2024Self-training from Self-memory in Data-to-text Generationcited by 0
  38. 2024Table-to-Text Generation with Pretrained Diffusion Modelscited by 0

50 most cited of 52 All 52 (JSON)