SEG-Doc: A simple yet efficient graph neural network framework for document key information extraction
Authors:
- Yangyang HuiYHYangyang Hui
- Jiahao LiuJLJiahao Liu
- Qi ZhangQZQi Zhang
- Tianyi ZhouTZTianyi Zhou
- Yonghong SongYSYonghong Song
- 26 May 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 647
Abstract
No abstract availableFunding Information
- Key Research and Development Projects of Shaanxi Province (2023-YBGY-029)
- Xi'an Jiaotong University
- National Natural Science Foundation of China (61973245)
This publication has 13 references indexed in Scilit:
- Multimodal weighted graph representation for information extraction from visually rich documentsNeurocomputing, 2024
- ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction2023
- Unifying Vision, Text, and Layout for Universal Document Processing2023
- GraphRevisedIE: Multimodal information extraction with graph-revised networkPattern Recognition, 2023
- LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking2022
- Split, Embed and Merge: An accurate table structure recognizerPattern Recognition, 2022
- SelfDoc: Self-Supervised Document Representation Learning2021
- Cardinal Graph Convolution Framework for Document Information Extraction2020
- FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents2019
- Mask R-CNN2017