mlsanityData to 14 Oct 2026

Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning

arXiv 2308.05317 ↗First posted 10 Aug 2023cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data. Our proposed method aims to improve performance in multi-task training, zero-shot and few-shot scenarios by providing a unified representation that can handle various forms of structured data such as tables, knowledge graph triples, and meaning representations. We demonstrate that our proposed approach can effectively adapt to new structured forms, and can improve performance in comparison to current methods. For example, our method resulted in a 66% improvement in zero-shot BLEU scores when transferring models trained on table inputs to a knowledge graph dataset. Our proposed method is an important step towards a more general data-to-text generation framework.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 49 of its 65 references that are in the map. First posted on arXiv 10 Aug 2023.

Builds on

49 of 65 references.

References · 49

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,046
  5. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  6. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 434
  7. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 428
  8. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 409
  9. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 398
  10. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 268
  11. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  12. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 145
37 more
  1. 2019Text Generation from Knowledge Graphs with Graph Transformerscited by 122
  2. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
  3. 2020Investigating Pretrained Language Models for Graph-to-Text Generationcited by 117
  4. 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
  5. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
  6. 2020Text-to-Text Pre-Training for Data-to-Text Taskscited by 104
  7. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  8. 2022TableFormer: Robust Transformer Modeling for Table-Text Encodingcited by 91
  9. 2020Logical Natural Language Generation from Open-Domain Tablescited by 90
  10. 2022Natural Language to Code Generation in Interactive Data Science Notebookscited by 87
  11. 2019Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challengecited by 86
  12. 2019Graph Transformer for Graph-to-Sequence Learningcited by 82
  13. 2019Semantic Noise Matters for Neural Natural Language Generationcited by 64
  14. 2021JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphscited by 58
  15. 2021HTLM: Hyper-Text Pre-Training and Prompting of Language Modelscited by 58
  16. 2018A Graph-to-Sequence Model for AMR-to-Text Generationcited by 56
  17. 2017Table-to-text Generation by Structure-aware Seq2seq Learningcited by 54
  18. 2021MATE: Multi-view Attention for Table Transformer Efficiencycited by 54
  19. 2019Few-Shot NLG with Pre-Trained Language Modelcited by 52
  20. 2019Neural data-to-text generation: A comparison between pipeline and end-to-end architecturescited by 51
  21. 2021Structural Adapters in Pretrained Language Models for AMR-to-text Generationcited by 48
  22. 2019Data-to-text Generation with Entity Modelingcited by 45
  23. 2018Table-to-Text: Describing Table Region with Natural Languagecited by 41
  24. 2020CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Trainingcited by 38
  25. 2022Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learningcited by 32
  26. 2020Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphscited by 30
  27. 2021Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Modelscited by 29
  28. 2019Enhancing AMR-to-Text Generation with Dual Graph Representationscited by 24
  29. 2021Neural Data-to-Text Generation with LM-based Text Augmentationcited by 22
  30. 2021Few-Shot Table-to-Text Generation with Prototype Memorycited by 21
  31. 2018End-to-End Content and Plan Selection for Data-to-Text Generationcited by 20
  32. 2022Table-To-Text generation and pre-training with TabT5cited by 20
  33. 2022Neural Pipeline for Zero-Shot Data-to-Text Generationcited by 19
  34. 2018Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalizationcited by 12
  35. 2020Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generationcited by 8
  36. 2022What Makes Data-to-Text Generation Hard for Pretrained Language Models?cited by 8
  37. 2018A Mixed Hierarchical Attention based Encoder-Decoder Approach for Standard Table Summarizationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practicescited by 20
  2. 2026Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Datacited by 0