mlsanityData to 14 Oct 2026

Spatial Information Integration in Small Language Models for Document Layout Generation and Classification

arXiv 2501.05497 ↗First posted 9 Jan 2025cs.CL cs.AI cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

Document layout understanding is a field of study that analyzes the spatial arrangement of information in a document hoping to understand its structure and layout. Models such as LayoutLM (and its subsequent iterations) can understand semi-structured documents with SotA results; however, the lack of open semi-structured data is a limitation in itself. While semi-structured data is common in everyday life (balance sheets, purchase orders, receipts), there is a lack of public datasets for training machine learning models for this type of document. In this investigation we propose a method to generate new, synthetic, layout information that can help overcoming this data shortage. According to our results, the proposed method performs better than LayoutTransformer, another popular layout generation method. We also show that, in some scenarios, text classification can improve when supported by bounding box information.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 42 references that are in the map. First posted on arXiv 9 Jan 2025.

Builds on

20 of 42 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  7. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  8. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 616
  9. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 553
  10. 2019PubLayNet: largest dataset ever for document layout analysiscited by 351
  11. 2019FUNSD: A Dataset for Form Understanding in Noisy Scanned Documentscited by 349
  12. 2023Self-Consuming Generative Models Go MADcited by 250
8 more
  1. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 153
  2. 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 131
  3. 2020LayoutTransformer: Layout Generation and Completion with Self-attentioncited by 123
  4. 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
  5. 2024A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'cited by 115
  6. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  7. 2024Many-Shot In-Context Learning in Multimodal Foundation Modelscited by 67
  8. 2022Explicitly incorporating spatial information to recurrent networks for agriculturecited by 4

Built on by

Not cited yet.