From Global to Local: Learning Context-Aware Graph Representations for Document Classification and Summarization

• URL: http://arxiv.org/abs/2603.00021v1
• Date: Tue, 03 Feb 2026 14:48:47 GMT
• Title: From Global to Local: Learning Context-Aware Graph Representations for Document Classification and Summarization
• Abstract summary: This paper proposes a data-driven method to automatically construct graph-based document representations.<n>We leverage the dynamic sliding-window attention module to capture semantic dependencies between sentences.<n>We present an exploratory evaluation of the proposed graph construction method for extractive document summarization.
• Score: 18.674554099946203
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper proposes a data-driven method to automatically construct graph-based document representations. Building upon the recent work of Bugueño and de Melo (2025), we leverage the dynamic sliding-window attention module to effectively capture local and mid-range semantic dependencies between sentences, as well as structural relations within documents. Graph Attention Networks (GATs) trained on our learned graphs achieve competitive results on document classification while requiring lower computational resources than previous approaches. We further present an exploratory evaluation of the proposed graph construction method for extractive document summarization, highlighting both its potential and current limitations. The implementation of this project can be found on GitHub.

Related papers

• GraphReAct: Reasoning and Acting for Multi-step Graph Inference [49.26607058250454]
  GraphReAct is a graph reasoning-acting framework that enables step-by-step inference over graph-structured data.<n>By interleaving reasoning with both retrieval and refinement actions, our framework enables a progressive transition from context expansion to compression.
  arXiv  Detail & Related papers  (2026-05-08T07:09:42Z)
• Graph-Anchored Knowledge Indexing for Retrieval-Augmented Generation [53.42323544075114]
  We propose GraphAnchor, a novel Graph-Anchored Knowledge Indexing approach.<n> Experiments on four multi-hop question answering benchmarks demonstrate the effectiveness of GraphAnchor.
  arXiv  Detail & Related papers  (2026-01-23T05:41:05Z)
• ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Links [57.514511353084565]
  We introduce a new domain-agnostic framework for selecting a best-performing approach and annotating cross-document links.<n>We apply our framework in two distinct domains -- peer review and news.<n>The resulting novel datasets lay foundation for numerous cross-document tasks like media framing and peer review.
  arXiv  Detail & Related papers  (2025-09-01T11:32:24Z)
• Rethinking Graph-Based Document Classification: Learning Data-Driven Structures Beyond Heuristic Approaches [21.922739597512955]
  We propose a method to learn data-driven graph structures, eliminating the need for manual design and reducing domain dependence.<n>Our approach constructs homogeneous weighted graphs with sentences as nodes, while edges are learned via a self-attention model that identifies dependencies between sentence pairs.
  arXiv  Detail & Related papers  (2025-07-18T12:05:54Z)
• Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level [3.7651378994837104]
  Long input hinders simultaneous modeling of both global high-order relations between sentences and local intra-sentence relations. We propose HAESum, a novel approach utilizing graph neural networks to model documents based on their hierarchical discourse structure. We validate our approach on two benchmark datasets, and the experimental results demonstrate the effectiveness of HAESum.
  arXiv  Detail & Related papers  (2024-05-16T15:46:30Z)
• 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)
• Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification [2.064612766965483]
  We propose a novel GNN-based sparse structure learning model for inductive document classification. Our model collects a set of trainable edges connecting disjoint words between sentences and employs structure learning to sparsely select edges with dynamic contextual dependencies. Experiments on several real-world datasets demonstrate that the proposed model outperforms most state-of-the-art results.
  arXiv  Detail & Related papers  (2021-12-13T02:36:04Z)
• A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction [9.449257113935461]
  We treat relations in a document as a relation graph among entities. The relation graph is iteratively constructed by editing edges of an initial graph. The way to edit edges is to classify them in a close-first manner.
  arXiv  Detail & Related papers  (2021-06-18T03:46:49Z)
• Self-supervised Graph-level Representation Learning with Local and Global Structure [71.45196938842608]
  We propose a unified framework called Local-instance and Global-semantic Learning (GraphLoG) for self-supervised whole-graph representation learning. Besides preserving the local similarities, GraphLoG introduces the hierarchical prototypes to capture the global semantic clusters. An efficient online expectation-maximization (EM) algorithm is further developed for learning the model.
  arXiv  Detail & Related papers  (2021-06-08T05:25:38Z)
• Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval [51.823187647843945]
  In this paper, we encode the neighborhood information with a graph-induced Gaussian distribution, and propose to integrate the two types of information with a graph-driven generative model. Under the approximation, we prove that the training objective can be decomposed into terms involving only singleton or pairwise documents, enabling the model to be trained as efficiently as uncorrelated ones.
  arXiv  Detail & Related papers  (2021-05-27T11:29:03Z)
• Leveraging Graph to Improve Abstractive Multi-Document Summarization [50.62418656177642]
  We develop a neural abstractive multi-document summarization (MDS) model which can leverage well-known graph representations of documents. Our model utilizes graphs to encode documents in order to capture cross-document relations, which is crucial to summarizing long documents. Our model can also take advantage of graphs to guide the summary generation process, which is beneficial for generating coherent and concise summaries.
  arXiv  Detail & Related papers  (2020-05-20T13:39:47Z)

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.