# Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents

arXiv: https://arxiv.org/abs/2403.15765 · HTML: https://mlsanity.com/paper/2403.15765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 43 of its 60 references that are in the map.
- First posted on arXiv 23 Mar 2024.

## Builds on (most cited first, 30 of 43)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training](https://mlsanity.com/paper/2007.07834/) (2020)
- [Few-NERD: A Few-Shot Named Entity Recognition Dataset](https://mlsanity.com/paper/2105.07464/) (2021)
- [LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding](https://mlsanity.com/paper/2202.13669/) (2022)
- [BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents](https://mlsanity.com/paper/2108.04539/) (2021)
- [Chargrid: Towards Understanding 2D Documents](https://mlsanity.com/paper/1809.08799/) (2018)
- [FewRel 2.0: Towards More Challenging Few-Shot Relation Classification](https://mlsanity.com/paper/1910.07124/) (2019)
- [StrucTexT: Structured Text Understanding with Multi-Modal Transformers](https://mlsanity.com/paper/2108.02923/) (2021)
- [ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery](https://mlsanity.com/paper/2011.14340/) (2020)
- [Graph Convolution for Multimodal Information Extraction from Visually Rich Documents](https://mlsanity.com/paper/1903.11279/) (2019)
- [LayoutReader: Pre-training of Text and Layout for Reading Order Detection](https://mlsanity.com/paper/2108.11591/) (2021)
- [FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction](https://mlsanity.com/paper/2203.08411/) (2022)
- [BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding](https://mlsanity.com/paper/1909.04948/) (2019)
- [Few-shot Text Classification with Distributional Signatures](https://mlsanity.com/paper/1908.06039/) (2019)
- [LAMBERT: Layout-Aware (Language) Modeling for information extraction](https://mlsanity.com/paper/2002.08087/) (2020)
- [Few-Shot Named Entity Recognition: A Comprehensive Study](https://mlsanity.com/paper/2012.14978/) (2020)
- [StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training](https://mlsanity.com/paper/2303.00289/) (2023)
- [ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents](https://mlsanity.com/paper/2105.11672/) (2021)
- [Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes](https://mlsanity.com/paper/2104.08481/) (2021)
- [Neural Snowball for Few-Shot Relation Learning](https://mlsanity.com/paper/1908.11007/) (2019)

## Abstract (arXiv)

Key-value relations are prevalent in Visually-Rich Documents (VRDs), often depicted in distinct spatial regions accompanied by specific color and font styles. These non-textual cues serve as important indicators that greatly enhance human comprehension and acquisition of such relation triplets. However, current document AI approaches often fail to consider this valuable prior information related to visual and spatial features, resulting in suboptimal performance, particularly when dealing with limited examples. To address this limitation, our research focuses on few-shot relational learning, specifically targeting the extraction of key-value relation triplets in VRDs. Given the absence of a suitable dataset for this task, we introduce two new few-shot benchmarks built upon existing supervised benchmark datasets. Furthermore, we propose a variational approach that incorporates relational 2D-spatial priors and prototypical rectification techniques. This approach aims to generate relation representations that are more aware of the spatial context and unseen relation in a manner similar to human perception. Experimental results demonstrate the effectiveness of our proposed method by showcasing its ability to outperform existing methods. This study also opens up new possibilities for practical applications.