Multimodal Pre-training Based on Graph Attention Network for Document Understanding

• URL: http://arxiv.org/abs/2203.13530v1
• Date: Fri, 25 Mar 2022 09:27:50 GMT
• Title: Multimodal Pre-training Based on Graph Attention Network for Document Understanding
• Authors: Zhenrong Zhang, Jiefeng Ma, Jun Du, Licheng Wang and Jianshu Zhang
• Abstract summary: GraphDoc is a graph-based model for various document understanding tasks. It is pre-trained in a multimodal framework by utilizing text, layout, and image information simultaneously. It learns a generic representation from only 320k unlabeled documents.
• Score: 32.55734039518983
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Document intelligence as a relatively new research topic supports many business applications. Its main task is to automatically read, understand, and analyze documents. However, due to the diversity of formats (invoices, reports, forms, etc.) and layouts in documents, it is difficult to make machines understand documents. In this paper, we present the GraphDoc, a multimodal graph attention-based model for various document understanding tasks. GraphDoc is pre-trained in a multimodal framework by utilizing text, layout, and image information simultaneously. In a document, a text block relies heavily on its surrounding contexts, so we inject the graph structure into the attention mechanism to form a graph attention layer so that each input node can only attend to its neighborhoods. The input nodes of each graph attention layer are composed of textual, visual, and positional features from semantically meaningful regions in a document image. We do the multimodal feature fusion of each node by the gate fusion layer. The contextualization between each node is modeled by the graph attention layer. GraphDoc learns a generic representation from only 320k unlabeled documents via the Masked Sentence Modeling task. Extensive experimental results on the publicly available datasets show that GraphDoc achieves state-of-the-art performance, which demonstrates the effectiveness of our proposed method.

Related papers

• GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation [14.511401955827875]
  Object detection in documents is a key step to automate the structural elements identification process. We present a graph-based knowledge distillation framework to correctly identify and localize the document objects in a document image.
  arXiv  Detail & Related papers  (2024-02-17T23:08:32Z)
• Enhancing Visually-Rich Document Understanding via Layout Structure Modeling [91.07963806829237]
  We propose GraphLM, a novel document understanding model that injects layout knowledge into the model. We evaluate our model on various benchmarks, including FUNSD, XFUND and CORD, and achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2023-08-15T13:53:52Z)
• Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs [79.0426838808629]
  We propose TAT-DQA, i.e. to answer the question over a visually-rich table-text document. Specifically, we propose a novel Doc2SoarGraph framework with enhanced discrete reasoning capability. We conduct extensive experiments on TAT-DQA dataset, and the results show that our proposed framework outperforms the best baseline model by 17.73% and 16.91% in terms of Exact Match (EM) and F1 score respectively on the test set.
  arXiv  Detail & Related papers  (2023-05-03T07:30:32Z)
• Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks [0.965964228590342]
  We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model. We evaluate our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection.
  arXiv  Detail & Related papers  (2022-08-23T19:48:10Z)
• Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis [4.920817773181236]
  Our Doc-GCN presents an effective way to harmonize and integrate heterogeneous aspects for Document Layout Analysis. We first construct graphs to explicitly describe four main aspects, including syntactic, semantic, density, and appearance/visual information. We apply graph convolutional networks for representing each aspect of information and use pooling to integrate them.
  arXiv  Detail & Related papers  (2022-08-22T07:22:05Z)
• Unified Pretraining Framework for Document Understanding [52.224359498792836]
  We present UDoc, a new unified pretraining framework for document understanding. UDoc is designed to support most document understanding tasks, extending the Transformer to take multimodal embeddings as input. An important feature of UDoc is that it learns a generic representation by making use of three self-supervised losses.
  arXiv  Detail & Related papers  (2022-04-22T21:47:04Z)
• SelfDoc: Self-Supervised Document Representation Learning [46.22910270334824]
  SelfDoc is a task-agnostic pre-training framework for document image understanding. Our framework exploits the positional, textual, and visual information of every semantically meaningful component in a document. It achieves superior performance on multiple downstream tasks with significantly fewer document images used in the pre-training stage compared to previous works.
  arXiv  Detail & Related papers  (2021-06-07T04:19:49Z)
• Extracting Summary Knowledge Graphs from Long Documents [48.92130466606231]
  We introduce a new text-to-graph task of predicting summarized knowledge graphs from long documents. We develop a dataset of 200k document/graph pairs using automatic and human annotations.
  arXiv  Detail & Related papers  (2020-09-19T04:37:33Z)
• DocBank: A Benchmark Dataset for Document Layout Analysis [114.81155155508083]
  We present textbfDocBank, a benchmark dataset that contains 500K document pages with fine-grained token-level annotations for document layout analysis. Experiment results show that models trained on DocBank accurately recognize the layout information for a variety of documents.
  arXiv  Detail & Related papers  (2020-06-01T16:04:30Z)
• Heterogeneous Graph Neural Networks for Extractive Document Summarization [101.17980994606836]
  Cross-sentence relations are a crucial step in extractive document summarization. We present a graph-based neural network for extractive summarization (HeterSumGraph) We introduce different types of nodes into graph-based neural networks for extractive document summarization.
  arXiv  Detail & Related papers  (2020-04-26T14:38:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.