mlsanityData to 7 Oct 2026

Coarse-to-Fine Decoding for Neural Semantic Parsing

arXiv 1805.04793 ↗First posted 12 May 2018cs.CLcited by 110

Not on the map. Why?

Abstract (arXiv)

Semantic parsing aims at mapping natural language utterances into structured meaning representations. In this work, we propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages. Given an input utterance, we first generate a rough sketch of its meaning, where low-level information (such as variable names and arguments) is glossed over. Then, we fill in missing details by taking into account the natural language input and the sketch itself. Experimental results on four datasets characteristic of different domains and meaning representations show that our approach consistently improves performance, achieving competitive results despite the use of relatively simple decoders.

Key facts. Cited by 110 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 42; 2022: 31; 2023: 22; 2024: 6; 2025: 4; 2026: 5.

110 papers.

Sort:

By area:

  1. 2022Natural Language to Code Translation with Executioncited by 122
  2. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 118
  3. 2022CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generationcited by 87
  4. 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 66
  5. 2021Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representationscited by 55
  6. 2022Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptionscited by 54
  7. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  8. 2021Improving Compositional Generalization with Latent Structure and Data Augmentationcited by 46
  9. 2023Prompting Large Language Models With the Socratic Methodcited by 43
  10. 2023Large Language Model-Aware In-Context Learning for Code Generationcited by 42
  11. 2021SpreadsheetCoder: Formula Prediction from Semi-structured Contextcited by 41
  12. 2022A Survey on Table Question Answering: Recent Advancescited by 41
38 more
  1. 2021LEWIS: Levenshtein Editing for Unsupervised Text Style Transfercited by 40
  2. 2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38
  3. 2021ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parsercited by 35
  4. 2024SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Modelscited by 32
  5. 2023Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generationcited by 27
  6. 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
  7. 2024PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistencycited by 26
  8. 2021Improving Text-to-SQL with Schema Dependency Learningcited by 25
  9. 2021Learning to Complete Code with Sketchescited by 23
  10. 2022Knowledge Base Question Answering: A Semantic Parsing Perspectivecited by 22
  11. 2023FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answeringcited by 21
  12. 2022UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQLcited by 20
  13. 2021Zero-Shot Cross-lingual Semantic Parsingcited by 19
  14. 2021FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretrainingcited by 19
  15. 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 19
  16. 2021Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsingcited by 18
  17. 2021Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Datacited by 17
  18. 2021Shellcode_IA32: A Dataset for Automatic Shellcode Generationcited by 16
  19. 2021Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsingcited by 15
  20. 2021A Two-Stage Approach towards Generalization in Knowledge Base Question Answeringcited by 15
  21. 2021Weakly Supervised Text-to-SQL Parsing through Question Decompositioncited by 15
  22. 2021On Robustness of Neural Semantic Parserscited by 14
  23. 2021Cost-effective End-to-end Information Extraction for Semi-structured Document Imagescited by 14
  24. 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
  25. 2022Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generationcited by 11
  26. 2022Explainable Abuse Detection as Intent Classification and Slot Fillingcited by 11
  27. 2023Generate, Transform, Answer: Question Specific Tool Synthesis for Tabular Datacited by 11
  28. 2021Context Transformer with Stacked Pointer Networks for Conversational Question Answering over Knowledge Graphscited by 10
  29. 2021Improving Tree-Structured Decoder Training for Code Generation via Mutual Learningcited by 10
  30. 2021Exploring Dynamic Selection of Branch Expansion Orders for Code Generationcited by 10
  31. 2021Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphscited by 10
  32. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  33. 2021Coarse-to-Fine Curriculum Learningcited by 9
  34. 2021Total Recall: a Customized Continual Learning Method for Neural Semantic Parserscited by 9
  35. 2021Question Answering for Complex Electronic Health Records Database using Unified Encoder-Decoder Architecturecited by 9
  36. 2021Toward Code Generation: A Survey and Lessons from Semantic Parsingcited by 8
  37. 2021Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generationcited by 8
  38. 2021Relation Aware Semi-autoregressive Semantic Parsing for NL2SQLcited by 8

50 most cited of 110 All 110 (JSON)