mlsanityData to 7 Oct 2026

Optimized Table Tokenization for Table Structure Recognition

arXiv 2305.03393 ↗First posted 5 May 2023cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

Extracting tables from documents is a crucial task in any document conversion pipeline. Recently, transformer-based models have demonstrated that table-structure can be recognized with impressive accuracy using Image-to-Markup-Sequence (Im2Seq) approaches. Taking only the image of a table, such models predict a sequence of tokens (e.g. in HTML, LaTeX) which represent the structure of the table. Since the token representation of the table structure has a significant impact on the accuracy and run-time performance of any Im2Seq model, we investigate in this paper how table-structure representation can be optimised. We propose a new, optimised table-structure language (OTSL) with a minimized vocabulary and specific rules. The benefits of OTSL are that it reduces the number of tokens to 5 (HTML needs 28+) and shortens the sequence length to half of HTML on average. Consequently, model accuracy improves significantly, inference time is halved compared to HTML-based models, and the predicted table structures are always syntactically correct. This in turn eliminates most post-processing needs.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 15 of its 24 references that are in the map. First posted on arXiv 5 May 2023.

Builds on

15 of 24 references.

References · 15

  1. 2019PubLayNet: largest dataset ever for document layout analysiscited by 349
  2. 2019Image-based table recognition: data, model, and evaluationcited by 233
  3. 2020Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Contextcited by 146
  4. 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 146
  5. 2021PubTables-1M: Towards comprehensive table extraction from unstructured documentscited by 122
  6. 2020CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documentscited by 98
  7. 2022TableFormer: Table Structure Understanding with Transformerscited by 93
  8. 2019Complicated Table Structure Recognitioncited by 91
  9. 2021Split, embed and merge: An accurate table structure recognizercited by 42
  10. 2021PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTMLcited by 39
  11. 2021TGRNet: A Table Graph Reconstruction Network for Table Structure Recognitioncited by 27
  12. 2018Corpus Conversion Service: A Machine Learning Platform to Ingest Documents at Scalecited by 12
3 more
  1. 2021Robust PDF Document Conversion Using Recurrent Neural Networkscited by 9
  2. 2022Delivering Document Conversion as a Cloud Service with High Throughput and Responsivenesscited by 7
  3. 2022Tables to LaTeX: structure and content extraction from scientific tablescited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 10; 2026: 18.

34 papers.

Sort:

By area:

  1. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsingcited by 108
  2. 2025SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversioncited by 51
  3. 2024Docling Technical Reportcited by 29
  4. 2025Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligencecited by 20
  5. 2024UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretrainingcited by 12
  6. 2025TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanismcited by 9
  7. 2026Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decodingcited by 9
  8. 2024SEMv3: A Fast and Robust Approach to Table Separation Line Detectioncited by 7
  9. 2025SPRINT: Script-agnostic Structure Recognition in Tablescited by 6
  10. 2025Advanced Layout Analysis Models for Doclingcited by 6
  11. 2025TABLET: Table Structure Recognition using Encoder-only Transformerscited by 5
  12. 2026ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervisioncited by 4
22 more
  1. 2026Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processingcited by 3
  2. 2023ESG Accountability Made Easy: DocQA at Your Servicecited by 2
  3. 2024PdfTable: A Unified Toolkit for Deep Learning-Based Table Extractioncited by 1
  4. 2026TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignmentcited by 1
  5. 2026Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Modelscited by 1
  6. 2026InstructTable: Improving Table Structure Recognition Through Instructionscited by 1
  7. 2026LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognitioncited by 1
  8. 2024MaterioMiner -- An ontology-based text mining dataset for extraction of process-structure-property entitiescited by 0
  9. 2025CISOL: An Open and Extensible Dataset for Table Structure Recognition in the Construction Industrycited by 0
  10. 2025SepFormer: Coarse-to-fine Separator Regression Network for Table Structure Recognitioncited by 0
  11. 2025Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Taskscited by 0
  12. 2026VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understandingcited by 0
  13. 2026TableSeq: Unified Generation of Structure, Content, and Layoutcited by 0
  14. 2026LIFT: Last-Mile Fine-Tuning for Table Explicitationcited by 0
  15. 2026FastTab: A Fast Table Recognizer with a Tiny Recursive Module and 1D Transformerscited by 0
  16. 2026Rethinking the Pointer Loss in Table Structure Recognition: Geometry-Aware Pointer Loss for Spatial Localitycited by 0
  17. 2026ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognitioncited by 0
  18. 2026From Diagnosis to Correction: Benchmarking and Improving Real-World Table Parsingcited by 0
  19. 2026TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documentscited by 0
  20. 2026Identify, Locate, Link: End-to-End Key-Value Extraction from Document Imagescited by 0
  21. 2026How Far Can Synthetic Data Take Thai OCR?cited by 0
  22. 2026Tables Decoded: DELTA for Structure, TARQA for Understandingcited by 0