mlsanityData to 14 Oct 2026

LAMBERT: Layout-Aware (Language) Modeling for information extraction

arXiv 2002.08087 ↗First posted 19 Feb 2020cs.CLcited by 53

Not on the map. Why?

Abstract (arXiv)

We introduce a simple new approach to the problem of understanding documents where non-trivial layout influences the local semantics. To this end, we modify the Transformer encoder architecture in a way that allows it to use layout features obtained from an OCR system, without the need to re-learn language semantics from scratch. We only augment the input of the model with the coordinates of token bounding boxes, avoiding, in this way, the use of raw images. This leads to a layout-aware language model which can then be fine-tuned on downstream tasks. The model is evaluated on an end-to-end information extraction task using four publicly available datasets: Kleister NDA, Kleister Charity, SROIE and CORD. We show that our model achieves superior performance on datasets consisting of visually rich documents, while also outperforming the baseline RoBERTa on documents with flat layout (NDA (F1) increase from 78.50 to 80.42). Our solution ranked first on the public leaderboard for the Key Information Extraction from the SROIE dataset, improving the SOTA (F1)-score from 97.81 to 98.17.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 22; 2023: 15; 2024: 7; 2025: 3; 2026: 1.

53 papers.

Sort:

By area:

  1. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 485
  2. 2022DiT: Self-supervised Pre-training for Document Image Transformercited by 152
  3. 2022Unifying Vision, Text, and Layout for Universal Document Processingcited by 140
  4. 2022Hierarchical multimodal transformers for Multi-Page DocVQAcited by 105
  5. 2024OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automationcited by 70
  6. 2022XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understandingcited by 68
  7. 2022FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extractioncited by 64
  8. 2021Document AI: Benchmarks, Models and Applicationscited by 62
  9. 2023DocILE Benchmark for Document Information Localization and Extractioncited by 58
  10. 2021MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understandingcited by 45
  11. 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
  12. 2023LMDX: Language Model-based Document Information Extraction and Localizationcited by 37
38 more
  1. 2022VRDU: A Benchmark for Visually-rich Document Understandingcited by 35
  2. 2021ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documentscited by 29
  3. 2022HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Informationcited by 26
  4. 2023Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answeringcited by 24
  5. 2024LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understandingcited by 24
  6. 2023Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Predictioncited by 23
  7. 2024DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understandingcited by 23
  8. 2023CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Datacited by 21
  9. 2023FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extractioncited by 20
  10. 2023DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documentscited by 19
  11. 2023DocTr: Document Transformer for Structured Information Extraction in Documentscited by 18
  12. 2022STable: Table Generation Framework for Encoder-Decoder Modelscited by 15
  13. 2022XDoc: Unified Pre-training for Cross-Format Document Understandingcited by 12
  14. 2022Business Document Information Extraction: Towards Practical Benchmarkscited by 11
  15. 2022Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Frameworkcited by 10
  16. 2022ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understandingcited by 9
  17. 2022MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understandingcited by 9
  18. 2023A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Imagescited by 9
  19. 2023GenKIE: Robust Generative Multimodal Document Key Information Extractioncited by 8
  20. 2024BuDDIE: A Business Document Dataset for Multi-task Information Extractioncited by 8
  21. 2022QueryForm: A Simple Zero-shot Form Entity Query Frameworkcited by 7
  22. 2022TRIE++: Towards End-to-End Information Extraction from Visually Rich Documentscited by 6
  23. 2023Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Modelscited by 6
  24. 2025Document Intelligence in the Era of Large Language Models: A Surveycited by 5
  25. 2024ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-trainingcited by 4
  26. 2021UNITER-Based Situated Coreference Resolution with Rich Multimodal Inputcited by 2
  27. 2023On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrievalcited by 2
  28. 2022LayoutXLM vs. GNN: An Empirical Evaluation of Relation Extraction for Documentscited by 1
  29. 2022Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Modelscited by 1
  30. 2023DocILE 2023 Teaser: Document Information Localization and Extractioncited by 1
  31. 2023GVdoc: Graph-based Visual Document Classificationcited by 1
  32. 2023Vision-Enhanced Semantic Entity Recognition in Document Images via Visually-Asymmetric Consistency Learningcited by 1
  33. 2024DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answeringcited by 1
  34. 2025KIEval: Evaluation Metric for Document Key Information Extractioncited by 1
  35. 2021LAME: Layout Aware Metadata Extraction Approach for Research Articlescited by 0
  36. 2022Radically Lower Data-Labeling Costs for Visually Rich Document Extraction Modelscited by 0
  37. 2022Semantic Table Detection with LayoutLMv3cited by 0
  38. 2022An Augmentation Strategy for Visually Rich Documentscited by 0

50 most cited of 53 All 53 (JSON)