mlsanityData to 7 Oct 2026

Data-to-text Generation with Variational Sequential Planning

arXiv 2202.13756 ↗First posted 28 Feb 2022cs.CLcited by 17

Not on the map. Why?

Abstract (arXiv)

We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, i.e., documents with multiple paragraphs, and propose a neural model enhanced with a planning component responsible for organizing high-level information in a coherent and meaningful way. We infer latent plans sequentially with a structured variational model, while interleaving the steps of planning and generation. Text is generated by conditioning on previous variational decisions and previously generated text. Experiments on two data-to-text benchmarks (RotoWire and MLB) show that our model outperforms strong baselines and is sample efficient in the face of limited training data (e.g., a few hundred instances).

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 43 of its 80 references that are in the map. First posted on arXiv 28 Feb 2022.

Builds on

43 of 80 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  6. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  7. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  8. 2015Pointer Networkscited by 882
  9. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  10. 2016Tutorial on Variational Autoencoderscited by 404
  11. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  12. 2021Recursively Summarizing Books with Human Feedbackcited by 287
31 more
  1. 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
  2. 2017Challenges in Data-to-Document Generationcited by 226
  3. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  4. 2021BookSum: A Collection of Datasets for Long-form Narrative Summarizationcited by 184
  5. 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
  6. 2018Bottom-Up Abstractive Summarizationcited by 177
  7. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  8. 2016Sequential Neural Models with Stochastic Layerscited by 115
  9. 2017Controllable Abstractive Summarizationcited by 110
  10. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
  11. 2020Sequential Latent Knowledge Selection for Knowledge-Grounded Dialoguecited by 82
  12. 2019Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generationcited by 75
  13. 2019Long and Diverse Text Generation with Planning-based Hierarchical Variational Modelcited by 62
  14. 2017Z-Forcing: Training Stochastic Recurrent Networkscited by 51
  15. 2019Data-to-text Generation with Entity Modelingcited by 45
  16. 2020A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systemscited by 34
  17. 2021Data-to-text Generation with Macro Planningcited by 34
  18. 2015What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignmentcited by 31
  19. 2019A Hierarchical Model for Data-to-Text Generationcited by 20
  20. 2017Deep Recurrent Generative Decoder for Abstractive Text Summarizationcited by 19
  21. 2020Variational Template Machine for Data-to-Text Generationcited by 19
  22. 2019Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)cited by 18
  23. 2020Posterior Control of Blackbox Generationcited by 16
  24. 2020Stepwise Extractive Summarization and Planning with Structured Transformerscited by 16
  25. 2019Learning to Select, Track, and Generate for Data-to-Textcited by 14
  26. 2018Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring?cited by 12
  27. 2020Latent Template Induction with Gumbel-CRFscited by 9
  28. 2021Generation Challenges: Results of the Accuracy Evaluation Shared Taskcited by 9
  29. 2019Findings of the Third Workshop on Neural Generation and Translationcited by 8
  30. 2019Improving Quality and Efficiency in Plan-based Neural Data-to-Text Generationcited by 7
  31. 2019Naver Labs Europe's Systems for the Document-Level Generation and Translation Task at WNGT 2019cited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 7; 2024: 2; 2025: 4; 2026: 1.

17 papers.

Sort:

  1. 2022Conditional Generation with a Question-Answering Blueprintcited by 44
  2. 2022ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situationscited by 36
  3. 2024Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generationcited by 16
  4. 2023Towards Verifiable Text Generation with Symbolic Referencescited by 13
  5. 2024Unifying Structured Data as Graph for Data-to-Text Pre-Trainingcited by 13
  6. 2025VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?cited by 11
  7. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  8. 2023μPLAN: Summarizing using a Content Plan as Cross-Lingual Bridgecited by 7
  9. 2023PixT3: Pixel-based Table-To-Text Generationcited by 6
  10. 2023Visual Storytelling with Question-Answer Planscited by 5
  11. 2023Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generationcited by 5
  12. 2025CoPERLex: Content Planning with Event-based Representations for Legal Case Summarizationcited by 4
5 more
  1. 2023Decomposed Prompting for Machine Translation Between Related Languages using Large Language Modelscited by 3
  2. 2023Learning from Multiple Sources for Data-to-Text and Text-to-Datacited by 1
  3. 2025Representing data in words: A context engineering approachcited by 1
  4. 2025Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approachcited by 0
  5. 2026Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domaincited by 0