mlsanityData to 7 Oct 2026

Natural Language to Structured Query Generation via Meta-Learning

arXiv 1803.02400 ↗First posted 2 Mar 2018cs.CL cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

In conventional supervised training, a model is trained to fit all the training examples. However, having a monolithic model may not always be the best strategy, as examples could vary widely. In this work, we explore a different learning protocol that treats each example as a unique pseudo-task, by reducing the original learning problem to a few-shot meta-learning scenario with the help of a domain-dependent relevance function. When evaluated on the WikiSQL dataset, our approach leads to faster convergence and achieves 1.1%-5.4% absolute accuracy gains over the non-meta-learning counterparts.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 18; 2022: 7; 2023: 4; 2024: 1; 2025: 3.

33 papers.

Sort:

By area:

  1. 2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 163
  2. 2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 105
  3. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 57
  4. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  5. 2021On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learningcited by 29
  6. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  7. 2023Robust Visual Question Answering: Datasets, Methods, and Future Challengescited by 23
  8. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  9. 2021ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learningcited by 18
  10. 2021Few Shot Dialogue State Tracking using Meta-learningcited by 16
  11. 2021On Robustness of Neural Semantic Parserscited by 14
  12. 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
21 more
  1. 2021Multi-modal Program Inference: a Marriage of Pre-trainedLanguage Models and Component-based Synthesiscited by 12
  2. 2022Meta-Learning a Cross-lingual Manifold for Semantic Parsingcited by 11
  3. 2021Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsingcited by 10
  4. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  5. 2021kFolden: k-Fold Ensemble for Out-Of-Distribution Detectioncited by 10
  6. 2022WildQA: In-the-Wild Video Question Answeringcited by 9
  7. 2021ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classificationcited by 8
  8. 2021ProtoTransformer: A Meta-Learning Approach to Providing Student Feedbackcited by 8
  9. 2023Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayescited by 8
  10. 2021Few-Shot Semantic Parsing for New Predicatescited by 7
  11. 2021SPARQLing Database Queries from Intermediate Question Decompositionscited by 7
  12. 2021Set-to-Sequence Methods in Machine Learning: a Reviewcited by 6
  13. 2021DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networkscited by 3
  14. 2021Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learningcited by 3
  15. 2023Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systemscited by 2
  16. 2022xDBTagger: Explainable Natural Language Interface to Databases Using Keyword Mappings and Schema Graphcited by 1
  17. 2022Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learningcited by 1
  18. 2024ERATTA: Extreme RAG for Table To Answers with Large Language Modelscited by 1
  19. 2025SynRAG: A Large Language Model Framework for Executable Query Generation in Heterogeneous SIEM Systemcited by 1
  20. 2023Is Meta-Learning the Right Approach for the Cold-Start Problem in Recommender Systems?cited by 0
  21. 2025Adaptive Clipping for Privacy-Preserving Few-Shot Learning: Enhancing Generalization with Limited Datacited by 0