mlsanityData to 7 Oct 2026

TAPAS: Weakly Supervised Table Parsing via Pre-training

arXiv 2004.02349 ↗First posted 5 Apr 2020cs.IR cs.AI cs.CLcited by 432

Not on the map. Why?

Cited by 54 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Answering natural language questions over tables is usually seen as a semantic parsing task. To alleviate the collection cost of full logical forms, one popular approach focuses on weak supervision consisting of denotations instead of logical forms. However, training semantic parsers from weak supervision poses difficulties, and in addition, the generated logical forms are only used as an intermediate step prior to retrieving the denotation. In this paper, we present TAPAS, an approach to question answering over tables without generating logical forms. TAPAS trains from weak supervision, and predicts the denotation by selecting table cells and optionally applying a corresponding aggregation operator to such selection. TAPAS extends BERT's architecture to encode tables as input, initializes from an effective joint pre-training of text segments and tables crawled from Wikipedia, and is trained end-to-end. We experiment with three different semantic parsing datasets, and find that TAPAS outperforms or rivals semantic parsing models by improving state-of-the-art accuracy on SQA from 55.1 to 67.2 and performing on par with the state-of-the-art on WIKISQL and WIKITQ, but with a simpler model architecture. We additionally find that transfer learning, which is trivial in our setting, from WIKISQL to WIKITQ, yields 48.7 accuracy, 4.2 points above the state-of-the-art.

Key facts. Cited by 432 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 65; 2022: 73; 2023: 71; 2024: 82; 2025: 82; 2026: 59.

432 papers.

Sort:

By area:

  1. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  2. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  3. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  4. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  5. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  6. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  7. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  8. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  9. 2022Binding Language Models in Symbolic Languagescited by 224
  10. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  11. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
  12. 2021MultiModalQA: Complex Question Answering over Text, Tables and Imagescited by 177
38 more
  1. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
  2. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  3. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 166
  4. 2023UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoningcited by 158
  5. 2022DePlot: One-shot visual language reasoning by plot-to-table translationcited by 157
  6. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  7. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  8. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
  9. 2021Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformercited by 134
  10. 2022MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derenderingcited by 132
  11. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  12. 2022A Survey of Deep Learning for Mathematical Reasoningcited by 124
  13. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 120
  14. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 117
  15. 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
  16. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
  17. 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
  18. 2024SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulationcited by 100
  19. 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
  20. 2022TableFormer: Robust Transformer Modeling for Table-Text Encodingcited by 90
  21. 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
  22. 2022MapQA: A Dataset for Question Answering on Choropleth Mapscited by 82
  23. 2025Dolphin: Document Image Parsing via Heterogeneous Anchor Promptingcited by 78
  24. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  25. 2021Open Domain Question Answering over Tables via Dense Retrievalcited by 74
  26. 2024ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoningcited by 68
  27. 2021Towards Few-Shot Fact-Checking via Perplexitycited by 63
  28. 2021Document AI: Benchmarks, Models and Applicationscited by 61
  29. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  30. 2023Generative Table Pre-training Empowers Models for Tabular Predictioncited by 55
  31. 2021MATE: Multi-view Attention for Table Transformer Efficiencycited by 54
  32. 2024Large Language Model for Table Processing: A Surveycited by 52
  33. 2024From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Modelscited by 52
  34. 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 51
  35. 2023SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tablescited by 51
  36. 2023Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMscited by 49
  37. 2022Reasoning Like Program Executorscited by 45
  38. 2021AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industrycited by 44

50 most cited of 432 All 432 (JSON)