mlsanityData to 7 Oct 2026

Data-to-text Generation by Splicing Together Nearest Neighbors

arXiv 2101.08248 ↗First posted 20 Jan 2021cs.CL cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token, left-to-right, we learn a policy that directly manipulates segments of neighbor text, by inserting or replacing them in partially constructed generations. Standard techniques for training such a policy require an oracle derivation for each generation, and we prove that finding the shortest such derivation can be reduced to parsing under a particular weighted context-free grammar. We find that policies learned in this way perform on par with strong baselines in terms of automatic and human evaluation, but allow for more interpretable and controllable generation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 47 of its 84 references that are in the map. First posted on arXiv 20 Jan 2021.

Builds on

47 of 84 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  7. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
  8. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  9. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  10. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  11. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  12. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
35 more
  1. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  2. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
  3. 2017Non-Autoregressive Neural Machine Translationcited by 457
  4. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 282
  5. 2017Toward Controlled Generation of Textcited by 271
  6. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 252
  7. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
  8. 2020Nearest Neighbor Machine Translationcited by 209
  9. 2019Levenshtein Transformercited by 197
  10. 2018Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinementcited by 194
  11. 2017Controlling Linguistic Style Aspects in Neural Language Generationcited by 147
  12. 2019Insertion Transformer: Flexible Sequence Generation via Insertion Operationscited by 123
  13. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
  14. 2017Controllable Abstractive Summarizationcited by 110
  15. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
  16. 2020Pre-training via Paraphrasingcited by 92
  17. 2017Generating Sentences by Editing Prototypescited by 88
  18. 2018Retrieve and Refine: Improved Sequence Generation Models For Dialoguecited by 82
  19. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  20. 2018Guiding Neural Machine Translation with Retrieved Translation Piecescited by 63
  21. 2018Learning Neural Templates for Text Generationcited by 61
  22. 2020Seq2Edits: Sequence Transduction Using Span-level Edit Operationscited by 58
  23. 2019Non-Monotonic Sequential Text Generationcited by 55
  24. 2019Controllable Paraphrase Generation with a Syntactic Exemplarcited by 44
  25. 2019Insertion-based Decoding with automatically Inferred Generation Ordercited by 43
  26. 2019Non-Parametric Adaptation for Neural Machine Translationcited by 34
  27. 2016Neural Machine Translation with Reconstructioncited by 28
  28. 2019Text Generation with Exemplar-based Adaptive Decodingcited by 28
  29. 2019Label-Agnostic Sequence Labeling by Copying Nearest Neighborscited by 27
  30. 2019Syntactically Supervised Transformers for Faster Neural Machine Translationcited by 19
  31. 2020Posterior Control of Blackbox Generationcited by 16
  32. 2020Learning Sparse Prototypes for Text Generationcited by 15
  33. 2016Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systemscited by 13
  34. 2020A Simple Approach to Case-Based Reasoning in Knowledge Basescited by 8
  35. 2020Exemplar Auditing for Multi-Label Biomedical Text Classificationcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1.

4 papers.

  1. 2023ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summariescited by 30
  2. 2022Nearest Neighbor Non-autoregressive Text Generationcited by 7
  3. 2022TempLM: Distilling Language Models into Template-Based Generatorscited by 4
  4. 2024A Systematic Review of Data-to-Text NLGcited by 4