Discourse-Aware Unsupervised Summarization of Long Scientific Documents

• URL: http://arxiv.org/abs/2005.00513v2
• Date: Wed, 13 Jan 2021 16:57:10 GMT
• Title: Discourse-Aware Unsupervised Summarization of Long Scientific Documents
• Abstract summary: We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents. Our method assumes a two-level hierarchical graph representation of the source document, and exploits asymmetrical positional cues to determine sentence importance. Results on the PubMed and arXiv datasets show that our approach outperforms strong unsupervised baselines by wide margins in automatic metrics and human evaluation.
• Score: 13.405733237855404
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents. Our method assumes a two-level hierarchical graph representation of the source document, and exploits asymmetrical positional cues to determine sentence importance. Results on the PubMed and arXiv datasets show that our approach outperforms strong unsupervised baselines by wide margins in automatic metrics and human evaluation. In addition, it achieves performance comparable to many state-of-the-art supervised approaches which are trained on hundreds of thousands of examples. These results suggest that patterns in the discourse structure are a strong signal for determining importance in scientific articles.

Related papers

• Asymmetric Within-Document Predictive Learning for Scientific Document Representation [16.276576840098247]
  We study predictive pretraining for scientific document representation using the discourse structure of papers.<n>We propose SciJEPA, a citation-free framework that learns through asymmetric within-document prediction.
  arXiv  Detail & Related papers  (2026-07-31T09:44:41Z)
• DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding [63.257540233507626]
  We propose a paradigm that requires the model to execute a structured Analysis, Localization and Reasoning workflow.<n>We show it robustly generalizes from short-page training to ultra-long documents and is naturally synergistic with visual Retrieval-Augmented Generation systems.
  arXiv  Detail & Related papers  (2026-04-14T14:39:26Z)
• SciFig: Towards Automating Scientific Figure Generation [41.73701976318102]
  SciFig is an end-to-end AI agent system that generates publication-ready pipeline figures directly from research paper texts.<n>We introduce a rubric-based evaluation framework that analyzes 2,219 real scientific figures to extract evaluation rubrics.<n>SciFig demonstrates remarkable performance: achieving 70.1$%$ overall quality on dataset-level evaluation and 66.2$%$ on paper-specific evaluation.
  arXiv  Detail & Related papers  (2026-01-07T20:56:58Z)
• 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)
• Contrastive Hierarchical Discourse Graph for Scientific Document Summarization [14.930704950433324]
  CHANGES is a contrastive hierarchical graph neural network for extractive scientific paper summarization. We also propose a graph contrastive learning module to learn global theme-aware sentence representations.
  arXiv  Detail & Related papers  (2023-05-31T20:54:43Z)
• MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents [77.34726150561087]
  We propose MIReAD, a simple method that learns high-quality representations of scientific papers. We train MIReAD on more than 500,000 PubMed and arXiv abstracts across over 2,000 journal classes.
  arXiv  Detail & Related papers  (2023-05-07T03:29:55Z)
• Scientific Paper Extractive Summarization Enhanced by Citation Graphs [50.19266650000948]
  We focus on leveraging citation graphs to improve scientific paper extractive summarization under different settings. Preliminary results demonstrate that citation graph is helpful even in a simple unsupervised framework. Motivated by this, we propose a Graph-based Supervised Summarization model (GSS) to achieve more accurate results on the task when large-scale labeled data are available.
  arXiv  Detail & Related papers  (2022-12-08T11:53:12Z)
• GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state [6.4805900740861]
  We propose GoSum, a reinforcement-learning-based extractive model for long-paper summarization. GoSum encodes states by building a heterogeneous graph from different discourse levels for each input document. We evaluate the model on two datasets of scientific articles summarization: PubMed and arXiv.
  arXiv  Detail & Related papers  (2022-11-18T14:07:29Z)
• 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)
• Enhancing Scientific Papers Summarization with Citation Graph [78.65955304229863]
  We redefine the task of scientific papers summarization by utilizing their citation graph. We construct a novel scientific papers summarization dataset Semantic Scholar Network (SSN) which contains 141K research papers in different domains. Our model can achieve competitive performance when compared with the pretrained models.
  arXiv  Detail & Related papers  (2021-04-07T11:13:35Z)
• What's New? Summarizing Contributions in Scientific Literature [85.95906677964815]
  We introduce a new task of disentangled paper summarization, which seeks to generate separate summaries for the paper contributions and the context of the work. We extend the S2ORC corpus of academic articles by adding disentangled "contribution" and "context" reference labels. We propose a comprehensive automatic evaluation protocol which reports the relevance, novelty, and disentanglement of generated outputs.
  arXiv  Detail & Related papers  (2020-11-06T02:23:01Z)
• SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression [61.97200991151141]
  SummPip is an unsupervised method for multi-document summarization. We convert the original documents to a sentence graph, taking both linguistic and deep representation into account. We then apply spectral clustering to obtain multiple clusters of sentences, and finally compress each cluster to generate the final summary.
  arXiv  Detail & Related papers  (2020-07-17T13:01:15Z)
• Learning Neural Textual Representations for Citation Recommendation [7.227232362460348]
  We propose a novel approach to citation recommendation using a deep sequential representation of the documents (Sentence-BERT) cascaded with Siamese and triplet networks in a submodular scoring function. To the best of our knowledge, this is the first approach to combine deep representations and submodular selection for a task of citation recommendation.
  arXiv  Detail & Related papers  (2020-07-08T12:38:50Z)

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.