mlsanityData to 7 Oct 2026

End-to-End Content and Plan Selection for Data-to-Text Generation

arXiv 1810.04700 ↗First posted 10 Oct 2018cs.CL cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents a survey of several extensions to sequence-to-sequence models to account for the latent content selection process, particularly variants of copy attention and coverage decoding. We further propose a training method based on diverse ensembling to encourage models to learn distinct sentence templates during training. An empirical evaluation of these techniques shows an increase in the quality of generated text across five automated metrics, as well as human evaluation.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 4; 2023: 1; 2024: 6.

20 papers.

Sort:

By area:

  1. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 117
  2. 2021Plan-then-Generate: Controlled Data-to-Text Generation via Planningcited by 52
  3. 2021Aspect-Controllable Opinion Summarizationcited by 47
  4. 2021Controlling Hallucinations at Word Level in Data-to-Text Generationcited by 41
  5. 2022Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learningcited by 32
  6. 2021Few-Shot Table-to-Text Generation with Prototype Memorycited by 21
  7. 2024Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challengescited by 18
  8. 2024LitLLMs, LLMs for Literature Review: Are we there yet?cited by 12
  9. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  10. 2021TCube: Domain-Agnostic Neural Time-series Narrationcited by 5
  11. 2024Text Style Transfer: An Introductory Overviewcited by 5
  12. 2024A Systematic Review of Data-to-Text NLGcited by 4
8 more
  1. 2021May the Force Be with Your Copy Mechanism: Enhanced Supervised-Copy Method for Natural Language Generationcited by 3
  2. 2024SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generationcited by 3
  3. 2022Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generationcited by 2
  4. 2023Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learningcited by 2
  5. 2021Transforming Multi-Conditioned Generation from Meaning Representationcited by 1
  6. 2021Generalising Multilingual Concept-to-Text NLG with Language Agnostic Delexicalisationcited by 1
  7. 2024Development of REGAI: Rubric Enabled Generative Artificial Intelligencecited by 1
  8. 2022Informative Text Generation from Knowledge Triplescited by 0