mlsanityData to 7 Oct 2026

Neural Pipeline for Zero-Shot Data-to-Text Generation

arXiv 2203.16279 ↗First posted 30 Mar 2022cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

In data-to-text (D2T) generation, training on in-domain data leads to overfitting to the data representation and repeating training data noise. We examine how to avoid finetuning pretrained language models (PLMs) on D2T generation datasets while still taking advantage of surface realization capabilities of PLMs. Inspired by pipeline approaches, we propose to generate text by transforming single-item descriptions with a sequence of modules trained on general-domain text-based operations: ordering, aggregation, and paragraph compression. We train PLMs for performing these operations on a synthetic corpus WikiFluent which we build from English Wikipedia. Our experiments on two major triple-to-text datasets -- WebNLG and E2E -- show that our approach enables D2T generation from RDF triples in zero-shot settings.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 53 of its 113 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

53 of 113 references.

References · 53

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  7. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  8. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  9. 2015Pointer Networkscited by 882
  10. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  11. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  12. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
38 more
  1. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 252
  2. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  3. 2018Higher-order Coreference Resolution with Coarse-to-fine Inferencecited by 150
  4. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 144
  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. 2020Neural CRF Model for Sentence Alignment in Text Simplificationcited by 106
  8. 2020Text-to-Text Pre-Training for Data-to-Text Taskscited by 104
  9. 2019Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challengecited by 86
  10. 2019Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generationcited by 75
  11. 2019Semantic Noise Matters for Neural Natural Language Generationcited by 64
  12. 2019Long and Diverse Text Generation with Planning-based Hierarchical Variational Modelcited by 62
  13. 2018Learning Neural Templates for Text Generationcited by 61
  14. 2021JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphscited by 58
  15. 2019Few-Shot NLG with Pre-Trained Language Modelcited by 52
  16. 2021Plan-then-Generate: Controlled Data-to-Text Generation via Planningcited by 52
  17. 2019Neural data-to-text generation: A comparison between pipeline and end-to-end architecturescited by 51
  18. 2021Changing the World by Changing the Datacited by 51
  19. 2020Logic2Text: High-Fidelity Natural Language Generation from Logical Formscited by 45
  20. 2020Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inferencecited by 43
  21. 2021Controlling Hallucinations at Word Level in Data-to-Text Generationcited by 41
  22. 2018Learning To Split and Rephrase From Wikipedia Edit Historycited by 38
  23. 2019Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialoguecited by 35
  24. 2020Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelitycited by 35
  25. 2019DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusioncited by 29
  26. 2020Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondencecited by 25
  27. 2021On Training Instance Selection for Few-Shot Neural Text Generationcited by 25
  28. 2017Split and Rephrasecited by 24
  29. 2016Neural Net Models for Open-Domain Discourse Coherencecited by 23
  30. 2021Neural Data-to-Text Generation with LM-based Text Augmentationcited by 22
  31. 2021Few-Shot Table-to-Text Generation with Prototype Memorycited by 21
  32. 2021Underreporting of errors in NLG output, and what to do about itcited by 19
  33. 2021Improving Compositional Generalization with Self-Training for Data-to-Text Generationcited by 19
  34. 2016Neural Sentence Orderingcited by 18
  35. 2016End-to-End Neural Sentence Ordering Using Pointer Networkcited by 17
  36. 2018Scalable Micro-planned Generation of Discourse from Structured Datacited by 12
  37. 2019CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoningcited by 12
  38. 2020Data-to-Text Generation with Iterative Text Editingcited by 11

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 8; 2024: 4; 2025: 3; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023HallE-Control: Controlling Object Hallucination in Large Multimodal Modelscited by 31
  2. 2023Language-Guided Music Recommendation for Video via Prompt Analogiescited by 18
  3. 2023Evaluating Generative Models for Graph-to-Text Generationcited by 16
  4. 2022ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Modelscited by 14
  5. 2022MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generationcited by 7
  6. 2022Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Modelscited by 6
  7. 2023PixT3: Pixel-based Table-To-Text Generationcited by 6
  8. 2024A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generationcited by 6
  9. 2024Narrating Causal Graphs with Large Language Modelscited by 4
  10. 2024PAGED: A Benchmark for Procedural Graphs Extraction from Documentscited by 4
  11. 2023You Can Generate It Again: Data-to-Text Generation with Verification and Correction Promptingcited by 2
  12. 2023Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learningcited by 2
7 more
  1. 2023Automatic Logical Forms improve fidelity in Table-to-Text generationcited by 2
  2. 2023ASPIRO: Any-shot Structured Parsing-error-Induced ReprOmpting for Consistent Data-to-Text Generationcited by 2
  3. 2024Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Modelcited by 2
  4. 2025Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systemscited by 1
  5. 2025JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industrycited by 0
  6. 2025LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generatorscited by 0
  7. 2026RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutationcited by 0